#882 by GitHub stars
desplega-ai/agent-swarm
Your Company Agentic Operating System
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
plugin/pi-skills/close-issue/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
plugin/pi-skills/create-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
plugin/pi-skills/implement-issue/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
plugin/pi-skills/investigate-sentry-issue/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
plugin/pi-skills/respond-github/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
plugin/pi-skills/review-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
plugin/pi-skills/start-leader/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
plugin/pi-skills/start-worker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
plugin/pi-skills/swarm-chat/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
plugin/pi-skills/todos/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
plugin/pi-skills/user-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
skills/agent-swarm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/community/open-prompt-showreel/skills/motion-design-replication/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/community/open-prompt-showreel/skills/motion-design-video-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/community/open-prompt-showreel/skills/video-generation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/extensions/task-digest/skills/task-digest-guide/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/skills/agent-browser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/skills/agentmail-sending/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/skills/apps/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/skills/attio-interaction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/skills/composio/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/skills/kapso-whatsapp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/skills/review-offered-task/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/skills/scheduled-task-resilience/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/skills/serply-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/skills/swarm-scripts/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
templates/skills/work-on-task/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
07b0f9829995 → 16634227d815
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 07b0f9829995
No earlier version was observed for comparison.
Verified commit 16634227d815217c6a6866c8d9d5d74635afad0e
git clone --filter=blob:none --no-checkout https://github.com/desplega-ai/agent-swarm.git .hotskills/desplega-ai-agent-swarm && git -C .hotskills/desplega-ai-agent-swarm checkout --detach 16634227d815217c6a6866c8d9d5d74635afad0e
# Copy each selected skill directory from .hotskills/desplega-ai-agent-swarm into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/desplega-ai/agent-swarm.git .hotskills/desplega-ai-agent-swarm && git -C .hotskills/desplega-ai-agent-swarm checkout --detach 16634227d815217c6a6866c8d9d5d74635afad0e
# Copy each selected skill directory from .hotskills/desplega-ai-agent-swarm into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/desplega-ai/agent-swarm.git .hotskills/desplega-ai-agent-swarm && git -C .hotskills/desplega-ai-agent-swarm checkout --detach 16634227d815217c6a6866c8d9d5d74635afad0e
# Copy each selected skill directory from .hotskills/desplega-ai-agent-swarm into .gemini/skills/<skill-name>/Heat
8.4- Star growth, last 7 daysAhead of 96% of tracked repositories
- Star growth, last 24 hoursAhead of 97% of tracked repositories
- Rank movement, last 7 daysAhead of 92% of tracked repositories
- Commits, last 30 daysAhead of 99% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- close-issue
plugin/pi-skills/close-issue - create-pr
plugin/pi-skills/create-pr - implement-issue
plugin/pi-skills/implement-issue - investigate-sentry-issue
plugin/pi-skills/investigate-sentry-issue - respond-github
plugin/pi-skills/respond-github - review-pr
plugin/pi-skills/review-pr - start-leader
plugin/pi-skills/start-leader - start-worker
plugin/pi-skills/start-worker - swarm-chat
plugin/pi-skills/swarm-chat - todos
plugin/pi-skills/todos - user-management
plugin/pi-skills/user-management - agent-swarm
skills/agent-swarm - motion-design-replication
templates/community/open-prompt-showreel/skills/motion-design-replication - motion-design-video-analysis
templates/community/open-prompt-showreel/skills/motion-design-video-analysis - open-prompt-showreel
templates/community/open-prompt-showreel/skills/open-prompt-showreel - video-generation
templates/community/open-prompt-showreel/skills/video-generation - task-digest-guide
templates/extensions/task-digest/skills/task-digest-guide - agent-browser
templates/skills/agent-browser - agentmail-sending
templates/skills/agentmail-sending - apps
templates/skills/apps - attio-interaction
templates/skills/attio-interaction - composio
templates/skills/composio - kapso-whatsapp
templates/skills/kapso-whatsapp - review-offered-task
templates/skills/review-offered-task - scheduled-task-resilience
templates/skills/scheduled-task-resilience - serply-search
templates/skills/serply-search - swarm-scripts
templates/skills/swarm-scripts - work-on-task
templates/skills/work-on-task
How it works
close-issue
When your agent uses it
Close a GitHub or GitLab issue with a summary comment
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
339 tokensWhen the skill is activated
Reference documents
14,346 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- Workflow
- Closing Reasons
- Tips
Scripts executed separately
../../../claude-mod/types/index.d.ts
Files
../../../.claude-plugin/marketplace.jsonasset594 bytes../../../.claude-plugin/plugin.jsonasset1,221 bytes../../../claude-mod/hooks.jsonasset34 bytes../../../claude-mod/types/index.d.tsruns1,350 bytes../../hooks/hooks.jsonasset1,413 bytesSKILL.mdcore1,370 bytesSKILL.mdcore1,370 bytes../../../skills/agent-swarm/SKILL.mddoc10,274 bytes../../../skills/agent-swarm/references/components.mddoc14,609 bytes../../../skills/agent-swarm/references/compose.mddoc5,793 bytes../../../skills/agent-swarm/references/helm.mddoc3,590 bytes../../../skills/agent-swarm/references/https.mddoc3,913 bytes../../../skills/agent-swarm/references/operate-k8s.mddoc8,329 bytes../../../skills/agent-swarm/references/slack.mddoc2,982 bytes../../../skills/agent-swarm/references/upgrade.mddoc6,917 bytes../../../skills/agent-swarm/references/usage.mddoc3,026 bytes
Read SKILL.md
# Close Issue
Close a GitHub or GitLab issue with an appropriate closing comment summarizing the resolution.
**Provider detection:** Check the URL or remote to determine the VCS provider:
- If GitHub → use `gh issue close` / `gh issue comment`
- If GitLab → use `glab issue close` / `glab issue note`
## Arguments
- `issue-number-or-url`: Either an issue number (e.g., `123`) or a full issue URL
## Workflow
View the complete source on GitHubcreate-pr
When your agent uses it
Create a pull request (GitHub) or merge request (GitLab) from the current branch
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
1,051 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- Prerequisites
- Workflow
- Tips
Scripts executed separately
../../../scripts/check-pr-body.ts
Files
SKILL.mdcore4,089 bytes../../../scripts/check-pr-body.tsruns14,188 bytes
Read SKILL.md
# Create Pull Request / Merge Request
Create a PR (GitHub) or MR (GitLab) from the current branch with an auto-generated title and description.
**Provider detection:** Check the remote URL:
- If `github.com` → use `gh` CLI
- If `gitlab.com` or `gitlab.` → use `glab` CLI
## Arguments
- `base-branch` (optional): Branch to merge into (defaults to `main` or repo default)
## Prerequisites
View the complete source on GitHubimplement-issue
When your agent uses it
Implement a GitHub issue or GitLab issue and create a PR/MR
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
664 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- Workflow
- Tips
Files
SKILL.mdcore2,740 bytes
Read SKILL.md
# Implement Issue
Read a GitHub or GitLab issue, implement the requested changes, and create a PR/MR.
**Provider detection:** Check the URL or remote:
- If GitHub → use `gh issue view` / `gh pr create`
- If GitLab → use `glab issue view` / `glab mr create`
## Arguments
- `issue-number-or-url`: Either an issue number (e.g., `123`) or a full URL
## Workflow
View the complete source on GitHubinvestigate-sentry-issue
When your agent uses it
Investigate and triage a Sentry error issue
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
591 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Arguments
- Workflow
- Search Query Syntax
- Tips
Files
SKILL.mdcore2,313 bytesSKILL.mdcore2,313 bytesSKILL.mdcore2,313 bytes
Read SKILL.md
# Investigate Sentry Issue
Investigate a Sentry issue to understand the error, gather context, and prepare for fixing or triaging.
## Prerequisites
`SENTRY_AUTH_TOKEN` and `SENTRY_ORG` must be set. Verify with `sentry-cli info`.
## Arguments
- `sentry-issue-url-or-id`: A Sentry issue URL or just the issue ID (e.g., `123456`)
## Workflow
View the complete source on GitHubrespond-github
When your agent uses it
Respond to a GitHub issue/PR or GitLab issue/MR
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
360 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- Workflow
- Decision Framework
- Tips
Files
SKILL.mdcore1,445 bytes
Read SKILL.md
# Respond to VCS Issue/PR/MR
Post a response to a GitHub issue/PR or GitLab issue/MR.
**Provider detection:** Check the URL or remote:
- If GitHub → use `gh issue comment` / `gh pr comment`
- If GitLab → use `glab issue note` / `glab mr note`
## Arguments
- `issue-or-pr-number-or-url`: Either a number (e.g., `123`) or a full URL
## Workflow
View the complete source on GitHubreview-pr
When your agent uses it
Review a pull request (GitHub) or merge request (GitLab) and provide detailed feedback
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
967 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- Workflow
- Tips
Files
SKILL.mdcore3,999 bytesSKILL.mdcore3,999 bytesSKILL.mdcore3,999 bytesSKILL.mdcore3,999 bytes
Read SKILL.md
# Review Pull Request / Merge Request
Review a PR (GitHub) or MR (GitLab) by analyzing changes and providing structured feedback.
**Provider detection:** Check the remote URL or provided URL:
- If GitHub → use `gh pr` commands
- If GitLab → use `glab mr` commands
## Arguments
- `pr-number-or-url`: Either a PR number (e.g., `123`) or a full URL
## Workflow
View the complete source on GitHubstart-leader
When your agent uses it
Start the Agent Swarm Leader
What it loads into context
Frontmatter
14 tokensAlways available to the agent
SKILL.md
861 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Initial Setup
- What to do next?
- Your Role as Leader
- Tools Reference
- Workflow
- Filesystem
- Communication Etiquette
Files
SKILL.mdcore3,919 bytes
Read SKILL.md
# Agent Swarm Leader Setup
# Initial disclaimer
If the `agent-swarm` MCP server is not configured or disabled, return immediately with the following message:
```
⚠<U+FE0F> The Agent Swarm MCP server is not configured or disabled.
```
## Initial Setup
You will be the leader of the agent swarm. Use the `agent-swarm` MCP server and call `join-swarm` with the lead flag and a funny, creative name indicating you are the leader. Use `my-agent-info` to verify registration.
View the complete source on GitHubstart-worker
When your agent uses it
Start an Agent Swarm Worker
What it loads into context
Frontmatter
13 tokensAlways available to the agent
SKILL.md
526 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Agent Swarm Worker Setup
- Tools Reference
- Workflow
- Filesystem
- Communication Etiquette
Files
SKILL.mdcore2,237 bytes
Read SKILL.md
# Agent Swarm Worker
# Initial disclaimer
If the `agent-swarm` MCP server is not configured or disabled, return immediately with the following message:
```
⚠<U+FE0F> The Agent Swarm MCP server is not configured or disabled.
```
## Agent Swarm Worker Setup
Before you even start you will need to ensure that you are registered in the swarm as a worker agent.
View the complete source on GitHubswarm-chat
When your agent uses it
Effective communication within the agent swarm using internal Slack
What it loads into context
Frontmatter
16 tokensAlways available to the agent
SKILL.md
382 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Parameters
- Example: Read all unread mentions
- Fallback
Files
SKILL.mdcore1,653 bytes
Read SKILL.md
# Swarm Chat
> These tools require the `messaging` capability on the API server, which is **disabled by default**. If they are missing, ask the operator to add `messaging` to the server's `CAPABILITIES` (the value replaces the default list — it is not additive).
Interact with the internal Slack-like chat system using the `agent-swarm` MCP server:
- `list-channels` — List all available chat channels
- `create-channel` — Create a new channel (empty `participants` adds all agents)
- `post-message` — Send a message to a channel
- `read-messages` — Read messages from a channel
## Key Parameters
**post-message:**View the complete source on GitHubtodos
When your agent uses it
Handle the agent personal todos.md file
What it loads into context
Frontmatter
13 tokensAlways available to the agent
SKILL.md
192 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Format
- Keep it tidy
- Fallback
Files
SKILL.mdcore767 bytes
Read SKILL.md
# Agent Personal Todos
File location: `/workspace/personal/todos.md`
## Format
```
# My TODOs
## Current
- [ ] Task 1
- [x] Task 2
- [ ] Task 3View the complete source on GitHubuser-management
When your agent uses it
How to manage the user registry — creating users for new Slack/GitHub/GitLab/Linear identities, managing aliases, resolving users across platforms. Use when a new human interacts with the swarm or when user identity needs updating.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
1,764 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Create Users
- Tools
- Workflow: New Slack User
- Workflow: New GitHub User
- Workflow: Linking Identities
- Important Notes
Files
SKILL.mdcore7,009 bytes
Read SKILL.md
# User Management
Manage the swarm's user registry — creating, updating, resolving, and listing users. Users link human identities across platforms (Slack, GitHub, GitLab, Linear, email) so the swarm can track who requested work.
> **Migration note (2026-05)**: the old top-level identity fields (`slackUserId`, `linearUserId`, `githubUsername`, `gitlabUsername`) and the fuzzy `name` lookup were removed in lockstep with the user-identity refactor. Use the new `{kind, externalId}` shape instead. Old payloads now fail Zod validation at runtime — there is no compatibility shim.
## When to Create Users
Create a new user when:
- An **unknown Slack user** sends a message to the swarm (`resolve-user` with `{kind: "slack", externalId: "<U_X>"}` returns no match)
- An **unknown GitHub user** opens an issue or PR that triggers a task
- An **unknown GitLab user** creates an issue or MR
- An **unknown Linear user** is assigned to or creates a synced issue
- A human explicitly asks to be registeredView the complete source on GitHubagent-swarm
When your agent uses it
Install, self-host, deploy, operate, or use agent-swarm. Covers Docker Compose, Kubernetes, configuration, coding agents, the admin UI, integrations, and connections.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
2,443 tokensWhen the skill is activated
Reference documents
11,903 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Install
- Use, in this order
Files
SKILL.mdcore10,274 bytesreferences/components.mddoc14,609 bytesreferences/compose.mddoc5,793 bytesreferences/helm.mddoc3,590 bytesreferences/https.mddoc3,913 bytesreferences/operate-k8s.mddoc8,329 bytesreferences/slack.mddoc2,982 bytesreferences/upgrade.mddoc6,917 bytesreferences/usage.mddoc3,026 bytes
Read SKILL.md
# Install and use agent-swarm
The repository at `main` is the authority. Re-fetch referenced files before acting because this installed skill is a snapshot.
Use the current examples when commands or options change. Mark completed checklist items. Record skipped optional items and the reason.
## Install
- [ ] **Required: establish the target.** Confirm the host, Compose or Kubernetes, harness, credentials, agent count, and private or public access. Default to every agent in the [Compose example](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml), the reference deployment (1 lead and 11 workers); trim only when the operator has a reason. These choices determine resources and networking. Read the [deployment guide](https://docs.agent-swarm.dev/docs/guides/deployment).
- [ ] **Required: check prerequisites.** Compose needs Git, Docker with Compose v2, OpenSSL, curl, and jq. Kubernetes needs kubectl, Helm, and persistent storage. Confirm capacity for the selected workers. Read the [Compose example](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml) and [chart values](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/values.yaml).
- [ ] **Required: assign component minimums.** Keep `.env` minimal: boot identity, authentication, encryption, URLs, and harness credentials. Set supported non-boot values through swarm config so the system can validate and reload them. Apply all three tiers in [component minimums](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/components.md).
- [ ] **Required: protect secrets and persistent data.** Generate an API key and preserve the encryption key with the database. Each agent needs its own personal volume, which holds the UUID it generates on first boot. The volume preserves identity and task recovery; the encryption key preserves encrypted credentials. Read [secrets encryption](https://docs.agent-swarm.dev/docs/guides/secrets-encryption) and [component minimums](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/components.md).
- [ ] **Required, choose one: Compose.** Clone the repository, copy `.env.docker.example`, set `API_KEY` and harness credentials (agent IDs are optional), then start the example services. The examples define the actual environment and volumes. Execute the [Compose procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/compose.md).
- [ ] **Required, choose one: Kubernetes.** Create the credential Secret and install `oci://ghcr.io/desplega-ai/charts/agent-swarm`. Pin the release with `--version`; omitting it takes the newest published chart. The image tag follows the chart `appVersion`, so the chart version is the pin. Use pool replicas to size workers. Execute the [Helm procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/helm.md). Follow [Kubernetes and Helm](https://github.com/desplega-ai/agent-swarm/blob/main/docs-site/content/docs/%28documentation%29/guides/kubernetes.mdx) for ingress, dashboard connection, and CORS.
- [ ] **Required: mount the API volume at `/app/data`, never `/app`.** A named volume shadows the image path it covers, so an `/app` mount freezes the image's `migrations/` and `package.json` at install time while the binary upgrades. The API then queries schema no migration created, and `/health` reports the stale version and stays green. Existing installs need a one-time data move. Execute the [pinning and upgrade procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/upgrade.md).View the complete source on GitHubmotion-design-replication
When your agent uses it
Rebuild the feel of a reference motion-design clip (camera, depth of field, easing, captions, outro) as an on-brand agent-swarm piece in Remotion, then prove it with side-by-side frames and a model re-read of the replica. Use when asked to "replicate this video's vibe for the swarm", "make one like this but ours", or to rebuild a competitor/product clip. Runs after motion-design-video-analysis.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
2,614 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 1 — analyse and write the rebuild spec
- Step 2 — pick the swarm subject and map it onto the reference's metaphor
- Step 3 — collect real brand assets; never redraw
- Step 4 — build in your Remotion project
- Step 5 — build → look → critique, at least 3 rounds
- Step 6 — music and audio
- Step 7 — master and deliverables
- Step 8 — judge: re-analyse the replica
Files
SKILL.mdcore10,130 bytes
Read SKILL.md
# Motion-design replication
Takes a reference clip and produces a replica that matches its craft (resolution, fps, duration, camera, DOF, easing, caption style, outro) while swapping everything brand-specific (palette, logo, shapes, copy) for agent-swarm's. Built on a run that rebuilt Linear's "Loops updates" dial as a Schedules teaser. Keep the working R3F + postprocessing + label setup from your first 3D composition in your Remotion project and reuse it.
The bar is the highest quality of content. A render that passes automated checks proves nothing about how it looks. The loop in Step 5 is the work.
## Step 1 — analyse and write the rebuild spec
Run `motion-design-video-analysis` on the reference, including its rebuild-spec section and the by-eye claim check. You need, in frames: every cut, every caption change, every transition window. Pull 10 fps windows around each transition; a cut hidden under a fast element reads as a "camera move" to both you and the model until you step frames.
## Step 2 — pick the swarm subject and map it onto the reference's metaphor
Pick the feature whose shape matches the reference's central object (a dial ⇒ Schedules, because a dial reads as a clock and a clock maps onto cron). Write captions that follow one real run of that feature, in product vocabulary, checked against the repo docs (`agent-swarm/docs-site/content/docs/`). Keep the reference's caption count and rhythm, not its words.
View the complete source on GitHubmotion-design-video-analysis
When your agent uses it
Reverse-engineer a short motion-design / product-update video (animation technique, timing and easing, composition, transitions, likely tooling, vibe, audio) and produce a rebuild spec someone can build from. Default path is one call to google/gemini-3.8-flash over sampled frames, then a mandatory by-eye check of every claim. Use when asked how a marketing or product video was made, what its vibe is, or before replicating one (then continue with motion-design-replication).
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
3,332 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Step 1 — probe the file
- Step 2 — audio: verify, then exercise transcription for real
- Step 3 — look at the whole clip yourself first
- Step 4 — default model call: google/gemini-3.8-flash over sampled frames
- Step 5 — check every model claim against the frames (mandatory)
- Step 6 — write the analysis
- Step 7 — the rebuild spec (required output section)
- Execution notes for an Agent Swarm worker
Files
SKILL.mdcore11,896 bytesSKILL.mdcore11,896 bytesSKILL.mdcore11,896 bytesSKILL.mdcore11,896 bytesSKILL.mdcore11,896 bytes
Read SKILL.md
# Motion-design video analysis
Turns a short (under ~1 min) motion-design clip into two things: an **analysis** (how it was made and how it feels) and a **rebuild spec** (numbers someone can build from without reopening the video). Validated on a 28.6 s product-update clip (Linear's "Loops updates") and reused as the judge on a replica of it.
The model is a fast first reader. You are the ground truth. Both models tested on the Linear clip confidently described a "flat 2D view that becomes 3D at 7.5s"; the frames show a 3D scene from t=0. Plan for that class of error.
## Prerequisites
- `ffmpeg` on PATH. Worker images have a full static build at `/usr/local/bin/ffmpeg` (has `fps`, `tile`, `scale`, `crop`, `hstack`; no `drawtext`, no `ffprobe`: read `ffmpeg -i` stderr, or run the community template's `setup.sh` to add ffprobe). The Remotion-bundled ffmpeg under `node_modules/@remotion/compositor-*` is stripped (no `fps`, `tile` or `hstack`); don't use it for analysis.
- Pixel maths: `python3 -m venv /tmp/venv && /tmp/venv/bin/pip install numpy pillow` (system pip is blocked by PEP 668; this venv install was run and works).
[Credential-related source omitted]
- Getting bytes off agent-fs: `agent-fs download <path> -o <file>`. Viewer URLs serve an SPA shell, not the file; use `agent-fs signed-url <path> --json` when a script needs to fetch it. Upload binaries with `agent-fs write <path> --file <local>` (binary-safe).
## Step 1 — probe the fileView the complete source on GitHubopen-prompt-showreel
When your agent uses it
Make a design-led motion-graphics video (showreel, eval comparison, feature or bug-hunt story) from one open prompt. Claude Opus at max effort designs, codes and renders the whole thing itself in a scratch dir, with no template and no repo PR. Use for any "make a video for X" / "do a showreel for Y" / "a little comparison video" ask aimed at X, LinkedIn or a launch post. Covers the Lead brief template, grounding every on-screen number in a real source, the real Agent Swarm end logo, CC0/CC BY music with credit, render specs (16:9 + 4:5), the contact-sheet self-critique loop, agent-fs delivery, feedback rounds and crash-safe retries. Not for fixed-template creatives or for replicating a reference clip.
What it loads into context
Frontmatter
191 tokensAlways available to the agent
SKILL.md
3,474 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use which skill
- Model, effort, harness
- Lead brief template
- Maker procedure
- Feedback rounds (v2, v3)
- Failures to avoid
Files
SKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytesSKILL.mdcore13,358 bytes
Read SKILL.md
# Open-prompt showreel videos
The approach: give a strong model on max effort one open creative prompt plus hard content rules, and let it design, code and render the whole video itself. Template pipelines produce generic cuts. This one produced the showreels and the TLA+ races cuts that the team liked.
## When to use which skill
| Ask | Skill |
|---|---|
| A video that should look designed: showreel, model/eval comparison, "we found N bugs", launch hype | **this skill** |
| A standard on-brand card or clip from a fixed template (release, proof stat, quote, OG image) | a template toolkit, if your swarm has one |
| Rebuild the feel of a reference clip someone linked | `motion-design-video-analysis`, then `motion-design-replication` |
| Repo-committed Remotion video (README hero, landing demo, case-study clip) | `video-generation` |
If the ask says "like the showreel", "your own design" or "go all out", or someone complained a cut looks generic, it is this skill.View the complete source on GitHubvideo-generation
When your agent uses it
How to generate repo-committed video content (README hero videos, case-study clips, landing demos) with Remotion. Covers project layout, fonts and colors that match the brand, audio sourcing, rendering in a worker container, the full-range yuvj420p gotcha, CI exclusions, and the "honest read" pacing principle. Use whenever you are asked to create a video from a Remotion project, animate a wireframe, or re-render an existing Remotion project. For a design-led one-off showreel use open-prompt-showreel instead.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
2,772 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Golden rules
- Project layout
- Bootstrapping a new video project
- Rendering in a worker container
- Fonts
- Theme tokens (dark palette, amber accent)
- Multiple compositions
- Audio
- Pacing: the "honest read"
- CI and repo integration
- README video embed (GitHub renderer gotchas)
- When to use what
- Common mistakes
Files
SKILL.mdcore10,318 bytesSKILL.mdcore10,318 bytesSKILL.mdcore10,318 bytesSKILL.mdcore10,318 bytesSKILL.mdcore10,318 bytesSKILL.mdcore10,318 bytesSKILL.mdcore10,318 bytes
Read SKILL.md
# Video generation (Remotion)
Remotion (React + TypeScript) is the stack for videos that live in a repo: README heroes, landing demos, case-study clips, thread dramatizations. `assets/video-source/` in `desplega-ai/agent-swarm` is the reference implementation; read it before starting a new project.
## Golden rules
1. **Remotion for repo-committed video.** `npx remotion studio` for previews, `remotion render` for mp4s. For a one-off design-led cut with no repo, use `open-prompt-showreel` instead.
2. **Ask for audio, don't pick it.** Music is a brand call. A person on the team chooses the track (CC0 or CC BY 4.0, for example from https://freesound.org). Never grab something yourself; ask. There is no default bed.
3. **Attribute in the video folder's README.** Artist name, source URL, license. Not in the repo root README; in the video project's own README.
4. **Design tokens mirror the product.** Pull colors and fonts from the product's own `globals.css` (Agent Swarm: Space Grotesk + Space Mono, zinc dark palette, amber `#f2a93b` accent). Do not invent new ones.
5. **Honest read pacing.** The first draft always over-packs the opening and under-weights the payoff. Compress setup scenes, expand the one that carries the message. See "Pacing" below.
6. **One Remotion project, many compositions.** Do not spin up a new repo per video. Register additional `<Composition>` entries in `src/Root.tsx` and add a `build:<slug>` script.
## Project layoutView the complete source on GitHubtask-digest-guide
When your agent uses it
Read the task-digest extension's output. Use when someone asks how many tasks completed or failed recently, or which agents did them.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
267 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Get a digest
- Read the result
Files
SKILL.mdcore1,074 bytesfiles/example-output.jsonasset217 bytes
Read SKILL.md
# Reading the task digest
The `task-digest` extension ships a script, a schedule and a workflow that count recent task outcomes.
## Get a digest
- Run the script: `script-run name="task-digest-collect" scope="global" args={"hours": 24}`.
- Or trigger the `task-digest-report` workflow; its `collect` step output holds the same result.
- The `task-digest-daily` schedule runs the script every day at 09:00 UTC while the extension is enabled.
## Read the result
| Field | Meaning |
|---|---|View the complete source on GitHubagent-browser
When your agent uses it
Drive a real browser with the agent-browser CLI (headless Chromium over CDP). Use for any browser task: verifying a UI change, taking a screenshot, walking a web page, filling a form, extracting page text, reproducing a frontend bug, or attaching UI evidence to a PR, issue, Linear comment, or Slack thread. Starts with a `command -v agent-browser` check and falls back to manual QA on the slim worker image. Screenshots are kept on agent-fs and embedded in GitHub as user attachments. This is the only browser automation tool; do not use qa-use.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
1,716 tokensWhen the skill is activated
Reference documents
1,584 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 0: check that the CLI is present
- Step 1: load the version-matched guide
- Step 2: the core loop
- Recording
- Step 3: share the screenshot through agent-fs
- Gotchas
Files
SKILL.mdcore6,922 bytesSKILL.mdcore6,922 bytesSKILL.mdcore6,922 bytesSKILL.mdcore6,922 bytesSKILL.mdcore6,922 bytesSKILL.mdcore6,922 bytesconfig.jsonasset900 bytescontent.mddoc6,331 bytes
Read SKILL.md
# agent-browser
`agent-browser` (vercel-labs) is the swarm's browser-automation CLI. It drives a headless Chromium over CDP and returns accessibility-tree snapshots with compact `@eN` refs. Use it for any browser task: verify a UI change, take a screenshot, walk a page, fill a form, extract page text, reproduce a frontend bug, or attach UI evidence to a PR, issue, Linear comment, or Slack thread.
Do not use `qa-use`. It is not installed in the worker image any more.
## Step 0: check that the CLI is present
The full worker image (`agent-swarm-worker:latest`) ships `agent-browser` and a headless Chromium. The slim image (`:slim`) has neither. The first command of any browser work is:
```bash
command -v agent-browser
```
View the complete source on GitHubagentmail-sending
When your agent uses it
Canonical AgentMail send-message API reference for swarm agents. Pins the base URL, required field names, text-only rendering workaround, BCC policy, and ready-to-copy curl / swarm-script examples so agents do not rediscover the API surface at runtime.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
1,336 tokensWhen the skill is activated
Reference documents
1,268 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Canonical Base URL
- Canonical Send-Message Fields
- Rule 0: One-Shots Stay One-Shots
- Default Example: Raw curl
- Reusable Workflow Example: script_upsert
- BCC Policy
- Human Approval
- Checklist
- Common Errors
Files
SKILL.mdcore5,280 bytesSKILL.mdcore5,280 bytesconfig.jsonasset614 bytescontent.mddoc4,960 bytes
Read SKILL.md
# AgentMail Sending
## Canonical Base URL
Use this base URL exactly:
```text
https://api.agentmail.to/v0/
```
DO NOT use `api.agentmail.ai`. That host is a hallucination and will not send mail through AgentMail's current API.
## Canonical Send-Message Fields
View the complete source on GitHubapps
When your agent uses it
Build and iterate on schema-backed Swarm Apps with live models, named queries, custom actions, and json-render interfaces using the app-upsert, app-get, app-list, and app-patch tools.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
20,093 tokensWhen the skill is activated
Reference documents
20,044 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Tools and iteration loop
- Safe schema evolution and rollback
- Definition reference
- Component catalog (all 34)
- Layout & interactivity
- Bindings, sentinels, and action chains
- Patch semantics
- Worked example: ideas tracker
- View and screenshot a live app
Files
SKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesSKILL.mdcore78,187 bytesconfig.jsonasset490 bytescontent.mddoc77,970 bytes
Read SKILL.md
# Swarm Apps
Swarm Apps are persistent, agent-authored internal applications: a schema-backed row store, named queries, custom script/task actions, and a validated json-render interface served at `/apps/<id>`. Use an app when people need to view and change live records; use `create_page` for a static snapshot.
> **Capability gate**: app tools are available when the server's `CAPABILITIES` includes `pages` (for example `CAPABILITIES=core,task-pool,pages`). There is no separate `apps` capability. If these tools are absent from your MCP list, this is why.
## Tools and iteration loop
| Tool | Use it for |
|---|---|
| `app-list` | Discover apps by id, name, description, and timestamps. Definitions are omitted. |
| `app-get` | Read one complete stored definition before changing it. |
| `app-upsert` | Create an app, or replace an existing app's entire definition when you intentionally have the full desired state. |
| `app-patch` | Make a focused change while preserving everything not mentioned in the patch. Prefer this for iteration. |View the complete source on GitHubattio-interaction
When your agent uses it
Generic Attio CRM REST API v2 recipes for querying records, upserting companies/people/deals, writing notes/tasks/comments, managing lists, and handling webhooks.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
2,797 tokensWhen the skill is activated
Reference documents
2,745 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- TL;DR
- Authentication
- Core object slugs
- Common operations
- Webhooks
- Rate limits
- Operational rules
- Error handling
- Worked example: stale deal reactivation
- Related references
Files
SKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesSKILL.mdcore9,730 bytesconfig.jsonasset542 bytescontent.mddoc9,499 bytes
Read SKILL.md
# Attio Interaction (Read + Write)
Use this skill to read and write your Attio CRM through the REST API v2. Every read or write is a direct API call; agent-swarm does not maintain a separate Attio sync.
## TL;DR
1. Resolve `ATTIO_API_KEY` from swarm config before making calls.
2. Base URL: `https://api.attio.com/v2/`
[Credential-related source omitted]
4. Prefer upsert over create for People, Companies, and Deals: `PUT /v2/objects/{slug}/records` with `matching_attribute`.
5. Rate limits: 100 reads/sec, 25 writes/sec. Pace write bursts to roughly 15-20/sec.
6. Attribute values are arrays, even for scalar values: `[{ "value": 42 }]`, never `42`.
## AuthenticationView the complete source on GitHubcomposio
When your agent uses it
Use Composio from Agent Swarm through the `agent-swarm x composio` CLI route, the `swarm_x` MCP tool, or a registered `ctx.api.composio` script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router sessions, Connect Links, or connected accounts. This is the HUB skill — for Google apps see the sibling skills `composio-gmail`, `composio-google-calendar`, `composio-google-docs`.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
3,030 tokensWhen the skill is activated
Reference documents
2,897 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Model
- Resolve the user and connected account
- Two ways to call a tool — and when to use each
- Script connection surface
- Recipe A — Register a user + send Connect Links (one per toolkit)
- Recipe B — Verify connections / check status
- Recipe C — Link a Composio connection to a swarm user identity
- Workflow (Tool Router session path)
- Discovering tools for any toolkit
- Gotchas
- Guardrails
Files
SKILL.mdcore12,253 bytesSKILL.mdcore12,253 bytesSKILL.mdcore12,253 bytesSKILL.mdcore12,253 bytesSKILL.mdcore12,253 bytesSKILL.mdcore12,253 bytesSKILL.mdcore12,253 bytesSKILL.mdcore12,253 bytesSKILL.mdcore12,253 bytesconfig.jsonasset842 bytescontent.mddoc11,706 bytes
Read SKILL.md
# Composio
Hub skill for Composio-managed third-party app access from the swarm. Three call
surfaces are available when the deployment has enabled them:
- CLI: `agent-swarm x composio <METHOD> <path> [--body '<json>']`
- MCP: `swarm_x` with `target: "composio"`
- Script connection: `ctx.api.composio.<operationId>(args)` inside a swarm script
`COMPOSIO_API_KEY` is deployment-scoped and injected by the CLI/API process — you
never pass or see it. All paths are **relative** Composio REST paths.
> **Per-app playbooks (verified slugs + argument shapes + gotchas):**
> [[composio-gmail]] · [[composio-google-calendar]] · [[composio-google-docs]].View the complete source on GitHubkapso-whatsapp
When your agent uses it
How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and resolve contacts to swarm users. Canonical reference for ANY Kapso interaction beyond the thin `send-whatsapp-message` / `reply-whatsapp-message` MCP tools — for templates, media, reactions, typing, mark-as-read, signature verify, contact resolution, conversation history, drop to the REST recipes here. Use whenever a task references a WhatsApp message routed through Kapso, or when a workflow needs to reply on WhatsApp.
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
5,543 tokensWhen the skill is activated
Reference documents
5,375 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use MCP tools vs this skill's REST recipes
- Setup
- Inbound webhook payload (v2)
- Non-text message types
- Resolve a contact to a swarm user
- Read conversation context
- Send a free-form text (within the 24h session window)
- Sending media (image, document, audio, video)
- Mark as read + typing indicator
- Send a reaction
- Send a template (outside the 24h window)
- Webhook signature verification
- Reply etiquette
- Where this fits in the swarm
- Common gotchas
Files
SKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesSKILL.mdcore21,269 bytesconfig.jsonasset1,202 bytescontent.mddoc20,460 bytes
Read SKILL.md
# Kapso WhatsApp
Kapso (https://kapso.ai) is a WhatsApp platform vendor that fronts the Meta Cloud API. A swarm provisions one or more WhatsApp phone numbers and wires each one to either the native inbound handler or a workflow that dispatches a task per inbound message.
## When to use MCP tools vs this skill's REST recipes
The integration ships **thin MCP-tool wrappers for the common case only**:
| Tool | Use for |
|---|---|
| `send-whatsapp-message` | Free-form text within the 24h session window. |
| `reply-whatsapp-message` | Same as above but quote-threads to an inbound WAMID. |
| `register-kapso-number` / `unregister-kapso-number` | Provisioning a phone number's webhook + KV mapping. |
View the complete source on GitHubreview-offered-task
When your agent uses it
Turn prompt for an offered swarm task: read the offer, accept with task-action and start work-on-task, or reject with a reason.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
460 tokensWhen the skill is activated
Reference documents
420 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Example Accept Flow
- Example Reject Flow
- Important Notes
Files
SKILL.mdcore1,879 bytesconfig.jsonasset483 bytescontent.mddoc1,701 bytes
Read SKILL.md
# Review Offered Task
You have been offered a task. Your job is to review it and decide whether to accept or reject it based on your capabilities and current workload.
## Workflow
1. **Get task details**: Call the `get-task-details` tool with the provided `taskId` to understand what the task involves.
2. **Evaluate the task**: Consider:
- Does this task match your capabilities?
- Do you have the necessary context or access to complete it?
- Is the task description clear enough to proceed?
3. **Make a decision**:View the complete source on GitHubscheduled-task-resilience
When your agent uses it
Guardrails for polling, scheduled jobs, and long-running external operations. Use whenever a task waits on CI, builds, deploys, browser jobs, or another asynchronous API so work survives heartbeat checks without duplicate delivery.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
1,796 tokensWhen the skill is activated
Reference documents
1,742 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Rule 1 — Never use `ScheduleWakeup` with `delaySeconds >= 300`
- Rule 2 — Tag retry tasks with `reboot-retry`
- Rule 3 — Long polls must store progress every two to three minutes
- Rule 4 — Diagnose repeated scheduled-task failures before retrying
- Rule 5 — Check for duplicate delivery before posting
- Rule 6 — After the deliverable ships, complete and exit
- Rule 7 — Use fire-then-follow-up for slow external jobs
Files
SKILL.mdcore8,380 bytesSKILL.mdcore8,380 bytesSKILL.mdcore8,380 bytesconfig.jsonasset616 bytescontent.mddoc8,094 bytes
Read SKILL.md
# Scheduled Task Resilience
Use these rules whenever a scheduled or regular task polls or waits on a long-running operation. They prevent heartbeat collisions, lost work, duplicate delivery, and sessions that fail after holding an external job open too long.
## Rule 1 — Never use `ScheduleWakeup` with `delaySeconds >= 300`
The runtime heartbeat staleness threshold may sit near the same window as the model prompt-cache TTL. Sleeping for five minutes or longer can therefore look like a dead worker and cause the heartbeat sweep to fail the task mid-poll.
Instead:
- For waits under four minutes, run **one** bounded sleep of at most 240 seconds followed by a **single** status check, as one shell call, then return control to the agent turn.
- **Never batch sleeps into a single shell invocation.** A loop of five 240-second sleeps blocks the session for twenty minutes with no opportunity to record progress — the same staleness failure `ScheduleWakeup` causes, just spelled differently.
- Between cycles, record progress as described in Rule 3, then start the next cycle in the next turn.
- For genuinely long waits such as CI builds, releases, or deploys, prefer a durable workflow or a follow-up task over `ScheduleWakeup`.View the complete source on GitHubserply-search
When your agent uses it
Query real Google results through Serply, with separate endpoints for news (dated coverage) and scholar (citation counts). Use when the ranking itself, the publication date, or the citation count is the answer.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
1,215 tokensWhen the skill is activated
Reference documents
1,164 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use Serply vs. Exa vs. WebSearch
- Step 1. Get the API key
- Step 2. Web search
- Step 3. News and scholar
- Step 4. Pair with WebFetch
- Discipline: no fabrication
- Quick gotchas
Files
SKILL.mdcore4,619 bytesSKILL.mdcore4,619 bytesSKILL.mdcore4,619 bytesSKILL.mdcore4,619 bytesSKILL.mdcore4,619 bytesconfig.jsonasset529 bytescontent.mddoc4,366 bytes
Read SKILL.md
# Serply Search
Serply (https://serply.io) is a Google SERP API. It returns the ranked organic results for a keyword query, and exposes Google News and Google Scholar as separate endpoints. API reference: https://serply.io/docs
## When to use Serply vs. Exa vs. WebSearch
| Query shape | Use |
|---|---|
| "Companies building agent coordination layers" | Exa (conceptual, embedding match) |
| "Blogs that argue knowledge is not data" | Exa (argument-shape) |
| "What ranks on page 1 for `bun sqlite orm`" | **Serply** search (the ranking is the answer) |
| "Funding rounds for company X since June" | **Serply** news (named entity plus date) |
| "How heavily cited is paper Y" | **Serply** scholar (citation counts) |
| "What is the official Bun docs URL?" | WebSearch (one concrete lookup) |View the complete source on GitHubswarm-scripts
When your agent uses it
Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline `script-run`, named `script-upsert`, durable `launch-script-run`). Covers the script-vs-tool rubric, the authoring contract (`args` first, `ctx` second), the seed catalog, connections and secrets, files and bash over the agent-fs drive (`ctx.fs`, `ctx.sh`), `db_query`, and exposing a script as an API.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
4,913 tokensWhen the skill is activated
Reference documents
4,807 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to script
- Loading the tools
- Seed catalog
- Authoring contract
- Inline script pattern
- Named script pattern
- Secrets
- `db_query` for aggregation
- Progress from a script
- Exposing a script as an API
Files
SKILL.mdcore19,369 bytesSKILL.mdcore19,369 bytesSKILL.mdcore19,369 bytesSKILL.mdcore19,369 bytesSKILL.mdcore19,369 bytesSKILL.mdcore19,369 bytesSKILL.mdcore19,369 bytesconfig.jsonasset715 bytescontent.mddoc18,943 bytes
Read SKILL.md
# Swarm Scripts
A swarm script is TypeScript that runs out of process with a typed Swarm SDK. Only its return value enters your context. Use one when direct tool calls would repeat, flood your context, or need deterministic processing over many records.
## When to script
| Situation | Approach |
|---|---|
| 1 to 9 SDK calls, result fits in context | Direct tool calls. |
| 10 or more similar calls, bulk or fan-out | Script. Inline `script-run` for a one-off, a named script for reuse. |
| Fetch, parse, and transform heavy data | Script, or `ctx_*` (context-mode) when your harness has it. |
| One large web fetch | `ctx_fetch_and_index` (context-mode). |
| A schedule, workflow, or API script that reads or writes drive files | Script with `ctx.fs` and `ctx.sh`. |
| Multi-agent fan-out, parallel work, deterministic pipeline | Workflow. See `workflow-iterate`. |View the complete source on GitHubwork-on-task
When your agent uses it
Turn prompt for an assigned swarm task: find the task, gather context when the message lacks it, use the skill the task names, finish with one of the four endings.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
733 tokensWhen the skill is activated
Reference documents
687 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore3,298 bytesconfig.jsonasset491 bytescontent.mddoc3,091 bytes
Read SKILL.md
# Working on a task
The taskId follows the command. Without one, call `get-tasks` with `mineOnly: true` and take your `pending` or `in_progress` task. If there is none, say so and stop.
This message carries the task text, its attachments, its output format, and memories from past sessions. If it does not (you invoked this command yourself, or the context was compacted), run the `task-context-gathering` script with the taskId.
When the task names a skill (`researching`, `planning`, `implementing`), use it. Otherwise work directly.
Finish the task with one of the four endings in your operating contract: `completed`, `defer-task`, `request-human-input`, or `failed`. Then stop.
Resuming (a resume task, or work cut by a graceful shutdown): read the parent's last progress line, then re-read live state once (PR state and head SHA, branch, `git status`) before new work. Re-run controls only if the head moved. Never redo a pushed commit or open a second PR for the same branch. Store a progress line with branch, PR number and head SHA each time you push. A document task has no branch: its live state is the brief's agent-fs output path and the task attachments. Read the parent task's output and any agent-fs draft path it names before rewriting. Run `agent-fs ls` on that path, download any partial and extend it; a superseded parent with empty output and no draft means a rebuild, not an extension. Then list the task's local work directory: a shutdown can leave the newest draft only there, or leave cache files half-written. Parse every cache file, delete the ones that fail, and re-run only the stages whose output is missing. Never re-run collection steps that already produced artifacts. A render task (video, image, generated page) has no branch either: its live state is the local project directory plus the brief's agent-fs output. List both; timestamps are hints only. Before reusing an output, verify that it exists, is complete and valid, and corresponds to the current sources and render settings (for example, using recorded input/settings hashes). Download remote output and verify its bytes and provenance; agent-fs listing dates alone do not establish freshness. Re-render missing, invalid, incomplete or stale output. Hand over the live app link `${AGENT_FS_LIVE_URL}/file/~/<org>/<drive>/<path>` by default. Use a share link only when the requester asked for one or the reader has no agent-fs login: then reuse a usable one, and create a missing one or replace an expired, revoked or view-exhausted one without re-rendering a valid unchanged output. A task that covers several PRs re-reads every PR in scope (state, mergedAt, head SHA), not only the first: a PR that merged during the shutdown takes no more pushes. If your task's `model` differs from the parent's, say so in the output, because the result's provenance changed.
Write times in replies, outputs and defer notes in the requester's timezone when the Requester Profile names one, never raw UTC.
View the complete source on GitHubSkills included
- close-issue
- create-pr
- implement-issue
- investigate-sentry-issue
- respond-github
- review-pr
- start-leader
- start-worker
- swarm-chat
- todos
- user-management
- agent-swarm
- motion-design-replication
- motion-design-video-analysis
- open-prompt-showreel
- video-generation
- task-digest-guide
- agent-browser
- agentmail-sending
- apps
- attio-interaction
- composio
- kapso-whatsapp
- review-offered-task
- scheduled-task-resilience
- serply-search
- swarm-scripts
- work-on-task
Repository facts
- License
- MIT
- Created
- Dec 19, 2025
- Last pushed
- Nov 7, 2026
- Forks
- 155
- Open issues
- 24
- Project activity
- Active
Rank over the last 12 weeks
Now #882 · best #694 · down 76 in 30 days
- #893 on Nov 2
- #894 on Nov 3
- #886 on Nov 4
- #881 on Nov 5
- #878 on Nov 6
- #882 since Nov 7
80 earlier periods
- #689 on Aug 2
- #686 on Aug 8
- #694 on Aug 9
- #726 on Aug 10
- #731 on Aug 11
- #723 on Aug 12
- #722 on Aug 13
- #719 on Aug 14
- #691 on Aug 15
- #716 on Aug 16
- #725 on Aug 17
- #737 on Aug 18
- #724 on Aug 19
- #720 on Aug 20
- #694 on Aug 22
- #727 on Aug 23
- #747 on Aug 24
- #756 on Aug 25
- #745 on Aug 26
- #754 on Aug 27
- #778 on Aug 28
- #720 on Aug 30
- #756 on Aug 31
- #772 on Sep 1
- #752 on Sep 2
- #756 on Sep 3
- #735 on Sep 4
- #717 on Sep 5
- #744 on Sep 6
- #751 on Sep 7
- #776 on Sep 8
- #757 on Sep 9
- #769 on Sep 10
- #744 on Sep 11
- #740 on Sep 12
- #739 on Sep 13
- #766 on Sep 14
- #755 on Sep 15
- #763 on Sep 16
- #756 on Sep 17
- #737 on Sep 18
- #713 on Sep 19
- #724 on Sep 20
- #744 on Sep 21
- #766 on Sep 22
- #758 on Sep 23
- #729 on Sep 24
- #711 on Sep 25
- #708 on Sep 26
- #737 on Sep 27
- #756 on Sep 28
- #781 on Sep 29
- #766 on Sep 30
- #711 on Oct 1
- #731 on Oct 2
- #717 on Oct 3
- #743 on Oct 4
- #750 on Oct 5
- #766 on Oct 7
- #806 on Oct 8
- #773 on Oct 9
- #758 on Oct 11
- #775 on Oct 12
- #781 on Oct 13
- #790 on Oct 14
- #780 on Oct 15
- #784 on Oct 16
- #757 on Oct 17
- #744 on Oct 18
- #788 on Oct 19
- #793 on Oct 20
- #799 on Oct 21
- #774 on Oct 22
- #779 on Oct 23
- #739 on Oct 24
- #884 on Oct 25
- #891 from Oct 28 to Oct 29
- #888 on Oct 30
- #890 on Oct 31
- #891 on Nov 1
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 102 notes
plugin/pi-skills/close-issue/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugin/pi-skills/investigate-sentry-issue/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugin/pi-skills/investigate-sentry-issue/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugin/pi-skills/review-pr/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugin/pi-skills/review-pr/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugin/pi-skills/review-pr/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/motion-design-video-analysis/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/motion-design-video-analysis/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/motion-design-video-analysis/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/motion-design-video-analysis/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 1 dangerous shell commandin 1 file: video-generation/SKILL.md:71
- 505 network referencesin 29 files: skills/agent-swarm/references/components.md:16 skills/agent-swarm/SKILL.md:13 skills/agent-swarm/references/https.md:3 and 26 more
- No hidden or obfuscated text
- No instruction overrides
- 2 executable scriptsin 2 files: claude-mod/types/index.d.ts:1 scripts/check-pr-body.ts:1
- 268 references to secretsin 25 files: skills/agent-swarm/references/components.md:16 attio-interaction/SKILL.md:13 attio-interaction/content.md:7 and 22 more
- No requests to vote in Hot
Show all 776 signals by file
.claude-plugin/marketplace.json
.claude-plugin/plugin.json
- Network accessline 6
"name": "desplega.sh", "email": "contact@desplega.sh", "url": "https://github.com/desplega-ai" - Network accessline 7
"email": "contact@desplega.sh", "url": "https://github.com/desplega-ai" }, - Network accessline 8
"url": "https://github.com/desplega-ai" - Network accessline 9
}, "homepage": "https://github.com/desplega-ai/agent-swarm", "repository": "https://github.com/desplega-ai/agent-swarm", - Network accessline 10
"homepage": "https://github.com/desplega-ai/agent-swarm", - Network accessline 11
"repository": "https://github.com/desplega-ai/agent-swarm", - Network accessline 29
"type": "string", "title": "Swarm API URL", "description": "Only needed without an agent-swarm-user MCP entry, e.g. https://api.example.com", - Network accessline 30
"title": "Swarm API URL", "description": "Only needed without an agent-swarm-user MCP entry, e.g. https://api.example.com", "required": false - Network accessline 31
"description": "Only needed without an agent-swarm-user MCP entry, e.g. https://api.example.com",
claude-mod/types/index.d.ts
- Executable scriptline 1
Executable file
plugin/pi-skills/investigate-sentry-issue/SKILL.md
- Access to secretsline 12
[Credential-related source omitted] - Network accessline 22
If given a URL (`https://sentry.io/organizations/{org}/issues/{issue_id}/`), extract the issue ID. - Network accessline 32
Use `https://sentry.io/api/0/organizations/${SENTRY_ORG}/issues/<issue-id>/` for metadata (first/last seen, event count, user impact, status).
scripts/check-pr-body.ts
- Executable scriptline 1
#!/usr/bin/env bun
skills/agent-swarm/SKILL.md
- Network accessline 13
- [ ] **Required: establish the target.** Confirm the host, Compose or Kubernetes, harness, credentials, agent count, and private or public access. Default to every agent in the [Compose example](https://github.com/desplega-ai/agent-swarm/b - Network accessline 13
- [ ] **Required: establish the target.** Confirm the host, Compose or Kubernetes, harness, credentials, agent count, and private or public access. Default to every agent in the [Compose example](https://github.com/desplega-ai/agent-swarm/b - Network accessline 14
- [ ] **Required: check prerequisites.** Compose needs Git, Docker with Compose v2, OpenSSL, curl, and jq. Kubernetes needs kubectl, Helm, and persistent storage. Confirm capacity for the selected workers. Read the [Compose example](https:/ - Network accessline 14
- [ ] **Required: check prerequisites.** Compose needs Git, Docker with Compose v2, OpenSSL, curl, and jq. Kubernetes needs kubectl, Helm, and persistent storage. Confirm capacity for the selected workers. Read the [Compose example](https:/ - Network accessline 15
- [ ] **Required: assign component minimums.** Keep `.env` minimal: boot identity, authentication, encryption, URLs, and harness credentials. Set supported non-boot values through swarm config so the system can validate and reload them. App - Network accessline 15
- [ ] **Required: assign component minimums.** Keep `.env` minimal: boot identity, authentication, encryption, URLs, and harness credentials. Set supported non-boot values through swarm config so the system can validate and reload them. App - Network accessline 16
- [ ] **Required: protect secrets and persistent data.** Generate an API key and preserve the encryption key with the database. Each agent needs its own personal volume, which holds the UUID it generates on first boot. The volume preserves - Network accessline 16
- [ ] **Required: protect secrets and persistent data.** Generate an API key and preserve the encryption key with the database. Each agent needs its own personal volume, which holds the UUID it generates on first boot. The volume preserves - Network accessline 17
[Credential-related source omitted] - Network accessline 17
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Network accessline 18
- [ ] **Required, choose one: Kubernetes.** Create the credential Secret and install `oci://ghcr.io/desplega-ai/charts/agent-swarm`. Pin the release with `--version`; omitting it takes the newest published chart. The image tag follows the c - Network accessline 18
- [ ] **Required, choose one: Kubernetes.** Create the credential Secret and install `oci://ghcr.io/desplega-ai/charts/agent-swarm`. Pin the release with `--version`; omitting it takes the newest published chart. The image tag follows the c - Network accessline 19
- [ ] **Required: mount the API volume at `/app/data`, never `/app`.** A named volume shadows the image path it covers, so an `/app` mount freezes the image's `migrations/` and `package.json` at install time while the binary upgrades. The A - Network accessline 19
- [ ] **Required: mount the API volume at `/app/data`, never `/app`.** A named volume shadows the image path it covers, so an `/app` mount freezes the image's `migrations/` and `package.json` at install time while the binary upgrades. The A - Network accessline 20
- [ ] **Required: pin the image version.** On Compose, set `AGENT_SWARM_VERSION` in `.env` to a published release and confirm the API and every agent resolve the same tag. Blank means `latest`, which moves on every commit to `main` and is n - Network accessline 20
- [ ] **Required: pin the image version.** On Compose, set `AGENT_SWARM_VERSION` in `.env` to a published release and confirm the API and every agent resolve the same tag. Blank means `latest`, which moves on every commit to `main` and is n - Network accessline 21
- [ ] **Required: verify operation.** Check `/health`, authenticated `/api/agents`, and a completed task. A healthy API alone does not prove workers can execute tasks. Execute the [API verification procedure](https://github.com/desplega-ai/ - Network accessline 21
- [ ] **Required: verify operation.** Check `/health`, authenticated `/api/agents`, and a completed task. A healthy API alone does not prove workers can execute tasks. Execute the [API verification procedure](https://github.com/desplega-ai/ - Network accessline 22
- [ ] **Optional: co-deploy agent-fs.** Enable shared files, attachments, and search when agents need durable file exchange. Compose includes agent-fs and MinIO. Helm enables it through `agentFs.enabled`. Read [agent-fs deployment](https:// - Network accessline 22
- [ ] **Optional: co-deploy agent-fs.** Enable shared files, attachments, and search when agents need durable file exchange. Compose includes agent-fs and MinIO. Helm enables it through `agentFs.enabled`. Read [agent-fs deployment](https:// - Network accessline 23
- [ ] **Optional: select another harness.** Choose Codex, pi with OpenRouter, or Bedrock when your credentials or models require it. Read [harness configuration](https://docs.agent-swarm.dev/docs/guides/harness-configuration) and the [crede - Network accessline 23
- [ ] **Optional: select another harness.** Choose Codex, pi with OpenRouter, or Bedrock when your credentials or models require it. Read [harness configuration](https://docs.agent-swarm.dev/docs/guides/harness-configuration) and the [crede - Network accessline 24
- [ ] **Recommended: add HTTPS.** The hosted dashboard, OAuth callbacks, and webhooks need a public HTTPS API origin. Compose ships a Caddy `tls` profile; the chart has a cert-manager shortcut. Execute the [HTTPS procedure](https://github.c - Network accessline 24
- [ ] **Recommended: add HTTPS.** The hosted dashboard, OAuth callbacks, and webhooks need a public HTTPS API origin. Compose ships a Caddy `tls` profile; the chart has a cert-manager shortcut. Execute the [HTTPS procedure](https://github.c - Network accessline 25
- [ ] **Optional: use another deployment manager.** Use the [deployment guide](https://docs.agent-swarm.dev/docs/guides/deployment) for VPS proxies, Dokploy, and Coolify. Use [DEPLOYMENT.md](https://github.com/desplega-ai/agent-swarm/blob/m - Network accessline 25
- [ ] **Optional: use another deployment manager.** Use the [deployment guide](https://docs.agent-swarm.dev/docs/guides/deployment) for VPS proxies, Dokploy, and Coolify. Use [DEPLOYMENT.md](https://github.com/desplega-ai/agent-swarm/blob/m - Network accessline 26
- [ ] **Required before any upgrade: back up the database and encryption key.** Migrations are forward-only, so re-pinning to an older tag is not a rollback. The backup is. Execute the [upgrade procedure](https://github.com/desplega-ai/agen - Network accessline 26
- [ ] **Required before any upgrade: back up the database and encryption key.** Migrations are forward-only, so re-pinning to an older tag is not a rollback. The backup is. Execute the [upgrade procedure](https://github.com/desplega-ai/agen - Network accessline 27
- [ ] **Recommended on Kubernetes: learn day-2 operations.** Upgrades, scaling pools, credential rotation, backups, and the troubleshooting table live in the [Kubernetes operations procedure](https://github.com/desplega-ai/agent-swarm/blob/ - Network accessline 27
- [ ] **Recommended on Kubernetes: learn day-2 operations.** Upgrades, scaling pools, credential rotation, backups, and the troubleshooting table live in the [Kubernetes operations procedure](https://github.com/desplega-ai/agent-swarm/blob/ - Network accessline 28
- [ ] **Optional: add backups and telemetry.** Backups support recovery. OpenTelemetry exposes service activity. Read [chart backup settings](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md) and [OpenTeleme - Network accessline 28
- [ ] **Optional: add backups and telemetry.** Backups support recovery. OpenTelemetry exposes service activity. Read [chart backup settings](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md) and [OpenTeleme - Network accessline 32
- [ ] **Required: access the API through HTTP and MCP.** HTTP exposes `/docs` and `/openapi.json` on port 3013. MCP uses `/mcp`. Connect your coding agent with `bunx @desplega.ai/agent-swarm connect`. This gives your project access to the s - Network accessline 32
- [ ] **Required: access the API through HTTP and MCP.** HTTP exposes `/docs` and `/openapi.json` on port 3013. MCP uses `/mcp`. Connect your coding agent with `bunx @desplega.ai/agent-swarm connect`. This gives your project access to the s - Network accessline 33
- [ ] **Optional: connect the admin UI.** Point `https://app.agent-swarm.dev` at your API, or run `apps/ui` locally. Use it to inspect tasks, manage agents, and configure the deployment. Read the [UI guide](https://docs.agent-swarm.dev/docs - Network accessline 33
- [ ] **Optional: connect the admin UI.** Point `https://app.agent-swarm.dev` at your API, or run `apps/ui` locally. Use it to inspect tasks, manage agents, and configure the deployment. Read the [UI guide](https://docs.agent-swarm.dev/docs - Network accessline 34
- [ ] **Optional: enable Slack first.** Slack provides native task intake, replies, and steering. Import `slack-manifest.json`, create both tokens, configure the API, and send the bot a DM. Execute the [Slack procedure](https://github.com/d - Network accessline 34
- [ ] **Optional: enable Slack first.** Slack provides native task intake, replies, and steering. Import `slack-manifest.json`, create both tokens, configure the API, and send the bot a DM. Execute the [Slack procedure](https://github.com/d - Network accessline 35
- [ ] **Optional: enable GitHub or GitLab.** Connect repository events so agents can respond to development work. Read [GitHub](https://docs.agent-swarm.dev/docs/integrations/github), [GitLab](https://docs.agent-swarm.dev/docs/integrations/ - Network accessline 35
- [ ] **Optional: enable GitHub or GitLab.** Connect repository events so agents can respond to development work. Read [GitHub](https://docs.agent-swarm.dev/docs/integrations/github), [GitLab](https://docs.agent-swarm.dev/docs/integrations/ - Network accessline 36
- [ ] **Optional: enable other integrations.** Add the systems that supply your work. Read [Linear](https://docs.agent-swarm.dev/docs/integrations/linear), [Jira](https://docs.agent-swarm.dev/docs/integrations/jira), [AgentMail](https://doc - Network accessline 36
- [ ] **Optional: enable other integrations.** Add the systems that supply your work. Read [Linear](https://docs.agent-swarm.dev/docs/integrations/linear), [Jira](https://docs.agent-swarm.dev/docs/integrations/jira), [AgentMail](https://doc - Network accessline 37
- [ ] **Optional: add connections.** Register OpenAPI, GraphQL, or MCP services to give scripts typed access to external systems. Configure connections through the lead or Settings → Connections. Read [script connections](https://docs.agent - Network accessline 37
- [ ] **Optional: add connections.** Register OpenAPI, GraphQL, or MCP services to give scripts typed access to external systems. Configure connections through the lead or Settings → Connections. Read [script connections](https://docs.agent - Network accessline 38
- [ ] **Optional: go deeper.** Use durable capabilities when recurring work needs context or automation. Read [memory](https://docs.agent-swarm.dev/docs/architecture/memory), [workflows](https://docs.agent-swarm.dev/docs/concepts/workflows) - Network accessline 38
- [ ] **Optional: go deeper.** Use durable capabilities when recurring work needs context or automation. Read [memory](https://docs.agent-swarm.dev/docs/architecture/memory), [workflows](https://docs.agent-swarm.dev/docs/concepts/workflows)
skills/agent-swarm/references/components.md
- Network accessline 16
[Credential-related source omitted] - Network accessline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Network accessline 18
Read the [configuration loader](https://github.com/desplega-ai/agent-swarm/blob/main/src/http/core.ts), [config endpoint](https://github.com/desplega-ai/agent-swarm/blob/main/src/http/config.ts), and [reserved-key guard](https://github.com/ - Network accessline 18
Read the [configuration loader](https://github.com/desplega-ai/agent-swarm/blob/main/src/http/core.ts), [config endpoint](https://github.com/desplega-ai/agent-swarm/blob/main/src/http/config.ts), and [reserved-key guard](https://github.com/ - Network accessline 20
Workers fetch global and agent configuration for each task. Stored values override their container environment for that task. This does not guarantee that every process-level setting reloads. Preserve boot credentials and identity in deploy - Network accessline 20
Workers fetch global and agent configuration for each task. Stored values override their container environment for that task. This does not guarantee that every process-level setting reloads. Preserve boot credentials and identity in deploy - Network accessline 22
Read the [worker runner](https://github.com/desplega-ai/agent-swarm/blob/main/src/commands/runner.ts). - Network accessline 22
Read the [worker runner](https://github.com/desplega-ai/agent-swarm/blob/main/src/commands/runner.ts). - Access to secretsline 24
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Network accessline 27
[Credential-related source omitted] - Network accessline 27
[Credential-related source omitted] - Access to secretsline 27
[Credential-related source omitted] - Access to secretsline 27
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Network accessline 32
Use the [Slack procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/slack.md) for secret writes. - Network accessline 32
Use the [Slack procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/slack.md) for secret writes. - Network accessline 36
| Component and reason | A: boot environment or deployment minimum | B: prefer swarm config | C: optional | |---|---|---|---| | API: authenticate clients and preserve encrypted secrets. [Source](https://github.com/desplega-ai/agent-swarm/bl - Network accessline 36
| Component and reason | A: boot environment or deployment minimum | B: prefer swarm config | C: optional | |---|---|---|---| | API: authenticate clients and preserve encrypted secrets. [Source](https://github.com/desplega-ai/agent-swarm/bl - Network accessline 37
|---|---|---|---| | API: authenticate clients and preserve encrypted secrets. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml) | Set `API_KEY` in the examples. Compose requires the `encryption_key` f - Network accessline 37
|---|---|---|---| | API: authenticate clients and preserve encrypted secrets. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml) | Set `API_KEY` in the examples. Compose requires the `encryption_key` f - Network accessline 38
[Credential-related source omitted] - Network accessline 38
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Network accessline 39
| API URLs: make callbacks and browser links reach the right service. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/templates/configmap.yaml) | Supply worker `MCP_BASE_URL` at boot. Set API `MCP_BASE_URL` - Network accessline 39
| API URLs: make callbacks and browser links reach the right service. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/templates/configmap.yaml) | Supply worker `MCP_BASE_URL` at boot. Set API `MCP_BASE_URL` - Network accessline 40
| API volume: preserve SQLite and recovery state. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml) | Compose `swarm_api:/app`. Helm API PVC with one API replica and writable storage. | No configurati - Network accessline 40
| API volume: preserve SQLite and recovery state. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml) | Compose `swarm_api:/app`. Helm API PVC with one API replica and writable storage. | No configurati - Network accessline 41
| Agent services: preserve registration and task recovery. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml) | Per service: API key, API URL, role, harness credential, and a personal volume. The volum - Network accessline 41
| Agent services: preserve registration and task recovery. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml) | Per service: API key, API URL, role, harness credential, and a personal volume. The volum - Network accessline 42
| Worker volumes: retain personal files and share local work. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md) | Compose uses `swarm_logs:/logs`, `swarm_shared:/workspace/shared`, and a distinct `s - Network accessline 42
| Worker volumes: retain personal files and share local work. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md) | Compose uses `swarm_logs:/logs`, `swarm_shared:/workspace/shared`, and a distinct `s - Network accessline 44
Use [Settings → Configuration](https://docs.agent-swarm.dev/docs/ui/configuration) for catalog values. - Network accessline 44
Use [Settings → Configuration](https://docs.agent-swarm.dev/docs/ui/configuration) for catalog values. - Network accessline 49
Set only the credential set for the selected harness. Credentials authenticate model calls. Read the [environment example](https://github.com/desplega-ai/agent-swarm/blob/main/.env.docker.example) and [harness guide](https://docs.agent-swar - Network accessline 49
Set only the credential set for the selected harness. Credentials authenticate model calls. Read the [environment example](https://github.com/desplega-ai/agent-swarm/blob/main/.env.docker.example) and [harness guide](https://docs.agent-swar - Network accessline 50
Read the [environment example](https://github.com/desplega-ai/agent-swarm/blob/main/.env.docker.example) and [harness guide](https://docs.agent-swarm.dev/docs/guides/harness-configuration). - Network accessline 50
Read the [environment example](https://github.com/desplega-ai/agent-swarm/blob/main/.env.docker.example) and [harness guide](https://docs.agent-swarm.dev/docs/guides/harness-configuration). - Access to secretsline 54
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Access to secretsline 55
[Credential-related source omitted] - Access to secretsline 55
[Credential-related source omitted] - Access to secretsline 56
[Credential-related source omitted] - Access to secretsline 56
[Credential-related source omitted] - Network accessline 65
| Component and reason | A: boot minimum | B: prefer swarm config | C: optional | |---|---|---|---| | API embeddings: enable semantic memory search. [Provider](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/memory/providers/ope - Network accessline 65
| Component and reason | A: boot minimum | B: prefer swarm config | C: optional | |---|---|---|---| | API embeddings: enable semantic memory search. [Provider](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/memory/providers/ope - Network accessline 66
|---|---|---|---| | API embeddings: enable semantic memory search. [Provider](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/memory/providers/openai-embedding.ts) | None to boot. Without a usable key, search falls back to full- - Network accessline 66
|---|---|---|---| | API embeddings: enable semantic memory search. [Provider](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/memory/providers/openai-embedding.ts) | None to boot. Without a usable key, search falls back to full- - Network accessline 67
[Credential-related source omitted] - Network accessline 67
[Credential-related source omitted] - Access to secretsline 67
[Credential-related source omitted] - Access to secretsline 67
[Credential-related source omitted] - Network accessline 68
| Session summaries and memory rating: preserve context and score retrieved memories. [Credential resolver](https://github.com/desplega-ai/agent-swarm/blob/main/src/utils/internal-ai/credentials.ts) | No extra key to boot. The runtime can r - Network accessline 68
| Session summaries and memory rating: preserve context and score retrieved memories. [Credential resolver](https://github.com/desplega-ai/agent-swarm/blob/main/src/utils/internal-ai/credentials.ts) | No extra key to boot. The runtime can r - Network accessline 70
[Credential-related source omitted] - Network accessline 70
[Credential-related source omitted] - Access to secretsline 70
[Credential-related source omitted] - Access to secretsline 70
[Credential-related source omitted] - Access to secretsline 71
[Credential-related source omitted] - Access to secretsline 71
[Credential-related source omitted] - Network accessline 72
Read the [memory initialization](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/memory/index.ts) and [search fallback](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/memory/providers/sqlite-store.ts). - Network accessline 72
Read the [memory initialization](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/memory/index.ts) and [search fallback](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/memory/providers/sqlite-store.ts). - Network accessline 77
`MEMORY_RATER_MODEL` currently reads the worker process environment. Treat that override as a worker deployment setting and restart workers after changing it. This override applies to the shared internal-ai path. The opencode plugin uses it - Network accessline 77
`MEMORY_RATER_MODEL` currently reads the worker process environment. Treat that override as a worker deployment setting and restart workers after changing it. This override applies to the shared internal-ai path. The opencode plugin uses it - Network accessline 79
Read the [model resolver](https://github.com/desplega-ai/agent-swarm/blob/main/src/utils/internal-ai/models.ts) and [rater registry](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/memory/raters/registry.ts). - Network accessline 79
Read the [model resolver](https://github.com/desplega-ai/agent-swarm/blob/main/src/utils/internal-ai/models.ts) and [rater registry](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/memory/raters/registry.ts). - Network accessline 83
agent-fs provides shared files and searchable artifacts. It is optional. Read [co-deployment](https://docs.agent-swarm.dev/docs/guides/agent-fs-co-deployment) and the [provisioner](https://github.com/desplega-ai/agent-swarm/blob/main/src/be - Network accessline 83
agent-fs provides shared files and searchable artifacts. It is optional. Read [co-deployment](https://docs.agent-swarm.dev/docs/guides/agent-fs-co-deployment) and the [provisioner](https://github.com/desplega-ai/agent-swarm/blob/main/src/be - Network accessline 84
Read [co-deployment](https://docs.agent-swarm.dev/docs/guides/agent-fs-co-deployment) and the [provisioner](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/seed/agent-fs-provision.ts). - Network accessline 84
Read [co-deployment](https://docs.agent-swarm.dev/docs/guides/agent-fs-co-deployment) and the [provisioner](https://github.com/desplega-ai/agent-swarm/blob/main/src/be/seed/agent-fs-provision.ts). - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Network accessline 109
| Component and reason | A: boot requirement | B: preferred stored minimum | C: optional | |---|---|---|---| | Slack: native work intake and replies. [Guide](https://docs.agent-swarm.dev/docs/integrations/slack) | None beyond the API. | Glo - Network accessline 109
| Component and reason | A: boot requirement | B: preferred stored minimum | C: optional | |---|---|---|---| | Slack: native work intake and replies. [Guide](https://docs.agent-swarm.dev/docs/integrations/slack) | None beyond the API. | Glo - Network accessline 110
|---|---|---|---| | Slack: native work intake and replies. [Guide](https://docs.agent-swarm.dev/docs/integrations/slack) | None beyond the API. | Global secrets `SLACK_BOT_TOKEN` and `SLACK_APP_TOKEN`. Set `SLACK_DISABLE=false`. Reload reco - Network accessline 110
|---|---|---|---| | Slack: native work intake and replies. [Guide](https://docs.agent-swarm.dev/docs/integrations/slack) | None beyond the API. | Global secrets `SLACK_BOT_TOKEN` and `SLACK_APP_TOKEN`. Set `SLACK_DISABLE=false`. Reload reco - Network accessline 111
| Slack: native work intake and replies. [Guide](https://docs.agent-swarm.dev/docs/integrations/slack) | None beyond the API. | Global secrets `SLACK_BOT_TOKEN` and `SLACK_APP_TOKEN`. Set `SLACK_DISABLE=false`. Reload reconnects Socket Mode - Network accessline 111
| Slack: native work intake and replies. [Guide](https://docs.agent-swarm.dev/docs/integrations/slack) | None beyond the API. | Global secrets `SLACK_BOT_TOKEN` and `SLACK_APP_TOKEN`. Set `SLACK_DISABLE=false`. Reload reconnects Socket Mode - Network accessline 112
| GitHub: repository webhooks. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/src/github/app.ts) | Public webhook URL for inbound events. | `GITHUB_WEBHOOK_SECRET`. App reactions additionally need `GITHUB_APP_ID` and `GITHUB_ - Network accessline 112
| GitHub: repository webhooks. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/src/github/app.ts) | Public webhook URL for inbound events. | `GITHUB_WEBHOOK_SECRET`. App reactions additionally need `GITHUB_APP_ID` and `GITHUB_ - Network accessline 113
| GitLab: repository webhooks and API actions. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/src/gitlab/auth.ts) | Public webhook URL. | `GITLAB_WEBHOOK_SECRET` for inbound events, `GITLAB_TOKEN` for API actions. | `GITLAB_U - Network accessline 113
| GitLab: repository webhooks and API actions. [Source](https://github.com/desplega-ai/agent-swarm/blob/main/src/gitlab/auth.ts) | Public webhook URL. | `GITLAB_WEBHOOK_SECRET` for inbound events, `GITLAB_TOKEN` for API actions. | `GITLAB_U - Network accessline 114
[Credential-related source omitted] - Network accessline 114
[Credential-related source omitted] - Access to secretsline 114
[Credential-related source omitted] - Access to secretsline 114
[Credential-related source omitted] - Network accessline 115
[Credential-related source omitted] - Network accessline 115
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Network accessline 116
[Credential-related source omitted] - Network accessline 116
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted] - Network accessline 117
[Credential-related source omitted] - Network accessline 117
[Credential-related source omitted] - Access to secretsline 117
[Credential-related source omitted] - Access to secretsline 117
[Credential-related source omitted] - Network accessline 118
[Credential-related source omitted] - Network accessline 118
[Credential-related source omitted] - Access to secretsline 118
[Credential-related source omitted] - Access to secretsline 118
[Credential-related source omitted] - Network accessline 119
| Connections: extend scripts with external services. [Guide](https://docs.agent-swarm.dev/docs/guides/script-connections) | None beyond the API. | Settings → Connections defines OpenAPI, GraphQL, or MCP endpoints and authentication. | Comp - Network accessline 119
| Connections: extend scripts with external services. [Guide](https://docs.agent-swarm.dev/docs/guides/script-connections) | None beyond the API. | Settings → Connections defines OpenAPI, GraphQL, or MCP endpoints and authentication. | Comp
skills/agent-swarm/references/compose.md
- Network accessline 3
Re-fetch the [Compose example](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml) and [environment example](https://github.com/desplega-ai/agent-swarm/blob/main/.env.docker.example) before acting. The Compose e - Network accessline 3
Re-fetch the [Compose example](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml) and [environment example](https://github.com/desplega-ai/agent-swarm/blob/main/.env.docker.example) before acting. The Compose e - Network accessline 8
git clone https://github.com/desplega-ai/agent-swarm.git - Network accessline 8
git clone https://github.com/desplega-ai/agent-swarm.git - Access to secretsline 10
[Credential-related source omitted] - Access to secretsline 10
[Credential-related source omitted] - Access to secretsline 12
[Credential-related source omitted] - Access to secretsline 12
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Network accessline 21
The API service must mount `swarm_api_data:/app/data`. An older install mounting `swarm_api:/app` shadows the image's `migrations/` and `package.json`, so its code upgrades while its migrations stay frozen at install time. `/health` reads t - Network accessline 21
The API service must mount `swarm_api_data:/app/data`. An older install mounting `swarm_api:/app` shadows the image's `migrations/` and `package.json`, so its code upgrades while its migrations stay frozen at install time. `/health` reads t - Network accessline 22
Existing installs need a one-time data move before starting. Execute the [pinning and upgrade procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/upgrade.md). - Network accessline 22
Existing installs need a one-time data move before starting. Execute the [pinning and upgrade procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/upgrade.md). - Network accessline 34
Pick a version from the [releases](https://github.com/desplega-ai/agent-swarm/releases). Confirm every service resolved the same tag: - Network accessline 34
Pick a version from the [releases](https://github.com/desplega-ai/agent-swarm/releases). Confirm every service resolved the same tag: - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Network accessline 41
Changing this value later is an upgrade, not a restart. Back up the database and encryption key first, and read the [pinning and upgrade procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/upgrade.m - Network accessline 41
Changing this value later is an upgrade, not a restart. Back up the database and encryption key first, and read the [pinning and upgrade procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/upgrade.m - Network accessline 62
Set `MCP_BASE_URL=http://localhost:3013` in `.env`. The API container uses this address for internal calls. - Network accessline 62
Set `MCP_BASE_URL=http://localhost:3013` in `.env`. The API container uses this address for internal calls. - Network accessline 63
Workers in the example already use `http://api:3013` for `MCP_BASE_URL`. - Network accessline 63
Workers in the example already use `http://api:3013` for `MCP_BASE_URL`. - Network accessline 64
External clients need their own reachable API URL. Set `APP_URL` to the admin UI URL. For public callbacks and the hosted dashboard, set `PUBLIC_MCP_BASE_URL=<public-https-api-url>` in `.env`. The example passes it to the API service. For a - Network accessline 64
External clients need their own reachable API URL. Set `APP_URL` to the admin UI URL. For public callbacks and the hosted dashboard, set `PUBLIC_MCP_BASE_URL=<public-https-api-url>` in `.env`. The example passes it to the API service. For a - Network accessline 65
For public callbacks and the hosted dashboard, set `PUBLIC_MCP_BASE_URL=<public-https-api-url>` in `.env`. The example passes it to the API service. For automatic certificates, use the Caddy `tls` profile described in the [HTTPS procedure]( - Network accessline 65
For public callbacks and the hosted dashboard, set `PUBLIC_MCP_BASE_URL=<public-https-api-url>` in `.env`. The example passes it to the API service. For automatic certificates, use the Caddy `tls` profile described in the [HTTPS procedure]( - Network accessline 66
For automatic certificates, use the Caddy `tls` profile described in the [HTTPS procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/https.md). - Network accessline 66
For automatic certificates, use the Caddy `tls` profile described in the [HTTPS procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/https.md). - Network accessline 67
Read the [URL definitions](https://github.com/desplega-ai/agent-swarm/blob/main/src/utils/constants.ts) for internal calls, OAuth redirects, and webhooks. - Network accessline 67
Read the [URL definitions](https://github.com/desplega-ai/agent-swarm/blob/main/src/utils/constants.ts) for internal calls, OAuth redirects, and webhooks. - Network accessline 68
Apply the [component minimums](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/components.md) before starting services. - Network accessline 68
Apply the [component minimums](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/components.md) before starting services. - Network accessline 71
The example includes MinIO credentials for development. Replace them consistently in `minio`, `minio-init`, and `agent-fs` before external access. Signed image/PDF/video previews and downloads default to `https://${AGENT_FS_DOMAIN}` when `A - Network accessline 71
The example includes MinIO credentials for development. Replace them consistently in `minio`, `minio-init`, and `agent-fs` before external access. Signed image/PDF/video previews and downloads default to `https://${AGENT_FS_DOMAIN}` when `A - Network accessline 72
Signed image/PDF/video previews and downloads default to `https://${AGENT_FS_DOMAIN}` when `AGENT_FS_DOMAIN` is set, or `http://localhost:9000` otherwise. The bundled Caddy proxy routes `/agentfs/*` on the file domain to MinIO. Set `AGENT_F - Network accessline 72
Signed image/PDF/video previews and downloads default to `https://${AGENT_FS_DOMAIN}` when `AGENT_FS_DOMAIN` is set, or `http://localhost:9000` otherwise. The bundled Caddy proxy routes `/agentfs/*` on the file domain to MinIO. Set `AGENT_F - Access to secretsline 77
[Credential-related source omitted] - Access to secretsline 77
[Credential-related source omitted] - Access to secretsline 78
[Credential-related source omitted] - Access to secretsline 78
[Credential-related source omitted] - Network accessline 79
[Credential-related source omitted] - Network accessline 79
[Credential-related source omitted] - Access to secretsline 79
[Credential-related source omitted] - Access to secretsline 79
[Credential-related source omitted] - Access to secretsline 80
[Credential-related source omitted] - Access to secretsline 80
[Credential-related source omitted] - Network accessline 81
curl -fsS http://localhost:3013/health - Network accessline 81
curl -fsS http://localhost:3013/health - Network accessline 84
The example starts a lead, coder workers, content workers, and other specialist workers. Remove unwanted services before starting. Do not share personal volumes between agents. Preserve the API, worker, and agent-fs volumes described in [co - Network accessline 84
The example starts a lead, coder workers, content workers, and other specialist workers. Remove unwanted services before starting. Do not share personal volumes between agents. Preserve the API, worker, and agent-fs volumes described in [co - Network accessline 85
Do not share personal volumes between agents. Preserve the API, worker, and agent-fs volumes described in [component minimums](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/components.md). - Network accessline 85
Do not share personal volumes between agents. Preserve the API, worker, and agent-fs volumes described in [component minimums](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/components.md). - Network accessline 87
Continue with the authenticated agent check and first task in [API usage](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/usage.md). - Network accessline 87
Continue with the authenticated agent check and first task in [API usage](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/usage.md).
skills/agent-swarm/references/helm.md
- Network accessline 3
Re-fetch the [chart README](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md) and [values](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/values.yaml). - Network accessline 3
Re-fetch the [chart README](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md) and [values](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/values.yaml). - Access to secretsline 6
[Credential-related source omitted] - Access to secretsline 6
[Credential-related source omitted] - Access to secretsline 7
[Credential-related source omitted] - Access to secretsline 7
[Credential-related source omitted] - Network accessline 17
Follow [Kubernetes and Helm](https://github.com/desplega-ai/agent-swarm/blob/main/docs-site/content/docs/%28documentation%29/guides/kubernetes.mdx) for ingress, dashboard connection, and CORS. - Network accessline 17
Follow [Kubernetes and Helm](https://github.com/desplega-ai/agent-swarm/blob/main/docs-site/content/docs/%28documentation%29/guides/kubernetes.mdx) for ingress, dashboard connection, and CORS. - Network accessline 19
The reference deployment is the [Compose example](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml): 1 lead and 11 workers. The default `pools` deploy the same roster with one coder where it runs two; set `poo - Network accessline 19
The reference deployment is the [Compose example](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml): 1 lead and 11 workers. The default `pools` deploy the same roster with one coder where it runs two; set `poo - Network accessline 37
Omit `--version` for latest. To pin a release, use the same `--version` for both `helm show values` and `helm install`. The resource names above assume release `swarm` without a name override. Keep port forwarding active while you execute t - Network accessline 37
Omit `--version` for latest. To pin a release, use the same `--version` for both `helm show values` and `helm install`. The resource names above assume release `swarm` without a name override. Keep port forwarding active while you execute t - Network accessline 39
Keep port forwarding active while you execute the [API checks](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/usage.md). - Network accessline 39
Keep port forwarding active while you execute the [API checks](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/usage.md). - Network accessline 41
agent-fs, shared RWX storage, ingress, and Litestream are optional. Configure them through the [chart README](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md). - Network accessline 41
agent-fs, shared RWX storage, ingress, and Litestream are optional. Configure them through the [chart README](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md). - Network accessline 42
For a public API with HTTPS, set `ingress.host` and `ingress.certManager.clusterIssuer`, or set `config.publicMcpBaseUrl` when TLS terminates elsewhere. Execute the [HTTPS procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skil - Network accessline 42
For a public API with HTTPS, set `ingress.host` and `ingress.certManager.clusterIssuer`, or set `config.publicMcpBaseUrl` when TLS terminates elsewhere. Execute the [HTTPS procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skil - Network accessline 43
A full values file with every official pool, agent-fs on local disk, and cert-manager is in [values-all-workers-agent-fs.yaml](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/examples/values-all-workers-agent-fs.yaml - Network accessline 43
A full values file with every official pool, agent-fs on local disk, and cert-manager is in [values-all-workers-agent-fs.yaml](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/examples/values-all-workers-agent-fs.yaml - Network accessline 44
After installation, follow the [Kubernetes operations procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/operate-k8s.md) for upgrades, scaling, rotation, backups, and troubleshooting. - Network accessline 44
After installation, follow the [Kubernetes operations procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/operate-k8s.md) for upgrades, scaling, rotation, backups, and troubleshooting.
skills/agent-swarm/references/https.md
- Network accessline 3
The hosted dashboard at `https://app.agent-swarm.dev` is served over HTTPS. Browsers block a plain-HTTP API as mixed content. - Network accessline 3
The hosted dashboard at `https://app.agent-swarm.dev` is served over HTTPS. Browsers block a plain-HTTP API as mixed content. - Network accessline 4
OAuth redirects, inbound webhooks, and page links also need a public HTTPS origin. Set `PUBLIC_MCP_BASE_URL` to that origin. Workers keep the internal `MCP_BASE_URL`. Read the [Kubernetes guide](https://docs.agent-swarm.dev/docs/guides/kube - Network accessline 4
OAuth redirects, inbound webhooks, and page links also need a public HTTPS origin. Set `PUBLIC_MCP_BASE_URL` to that origin. Workers keep the internal `MCP_BASE_URL`. Read the [Kubernetes guide](https://docs.agent-swarm.dev/docs/guides/kube - Network accessline 6
Read the [Kubernetes guide](https://docs.agent-swarm.dev/docs/guides/kubernetes) and the [deployment guide](https://docs.agent-swarm.dev/docs/guides/deployment). - Network accessline 6
Read the [Kubernetes guide](https://docs.agent-swarm.dev/docs/guides/kubernetes) and the [deployment guide](https://docs.agent-swarm.dev/docs/guides/deployment). - Network accessline 10
The [Compose example](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml) contains a `caddy` service under the `tls` profile. - Network accessline 10
The [Compose example](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml) contains a `caddy` service under the `tls` profile. - Network accessline 14
With `AGENT_FS_DOMAIN` set, the default S3 public endpoint is `https://${AGENT_FS_DOMAIN}`. Without it, the default remains `http://localhost:9000`. A non-empty `AGENT_FS_S3_PUBLIC_ENDPOINT` overrides either default and must be an origin br - Network accessline 14
With `AGENT_FS_DOMAIN` set, the default S3 public endpoint is `https://${AGENT_FS_DOMAIN}`. Without it, the default remains `http://localhost:9000`. A non-empty `AGENT_FS_S3_PUBLIC_ENDPOINT` overrides either default and must be an origin br - Access to secretsline 17
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Network accessline 18
SWARM_API_DOMAIN=swarm-api.example.com AGENT_FS_DOMAIN=swarm-files.example.com PUBLIC_MCP_BASE_URL=https://swarm-api.example.com - Network accessline 18
SWARM_API_DOMAIN=swarm-api.example.com AGENT_FS_DOMAIN=swarm-files.example.com PUBLIC_MCP_BASE_URL=https://swarm-api.example.com - Network accessline 19
AGENT_FS_DOMAIN=swarm-files.example.com PUBLIC_MCP_BASE_URL=https://swarm-api.example.com ENV - Network accessline 19
AGENT_FS_DOMAIN=swarm-files.example.com PUBLIC_MCP_BASE_URL=https://swarm-api.example.com ENV - Network accessline 20
PUBLIC_MCP_BASE_URL=https://swarm-api.example.com - Network accessline 20
PUBLIC_MCP_BASE_URL=https://swarm-api.example.com - Network accessline 21
ENV docker compose -f docker-compose.example.yml --env-file .env --profile tls up -d curl -fsS https://swarm-api.example.com/health - Network accessline 21
ENV docker compose -f docker-compose.example.yml --env-file .env --profile tls up -d curl -fsS https://swarm-api.example.com/health - Access to secretsline 22
[Credential-related source omitted] - Access to secretsline 22
[Credential-related source omitted] - Network accessline 23
curl -fsS https://swarm-api.example.com/health - Network accessline 23
curl -fsS https://swarm-api.example.com/health - Network accessline 31
The chart adds the cert-manager annotation, generates the `tls` entry, and derives an `https://` public URL when an issuer is named. - Network accessline 31
The chart adds the cert-manager annotation, generates the `tls` entry, and derives an `https://` public URL when an issuer is named. - Network accessline 32
No TLS Secret is created by hand. Install [cert-manager](https://cert-manager.io/docs/installation/) and create a ClusterIssuer first. - Network accessline 32
No TLS Secret is created by hand. Install [cert-manager](https://cert-manager.io/docs/installation/) and create a ClusterIssuer first. - Network accessline 33
Read the [chart HTTPS section](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md). - Network accessline 33
Read the [chart HTTPS section](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md). - Network accessline 51
Use `certManager.issuer` for a namespaced Issuer. Explicit `ingress.tls` entries take precedence. A complete example is in [values-all-workers-agent-fs.yaml](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/examples/v - Network accessline 51
Use `certManager.issuer` for a namespaced Issuer. Explicit `ingress.tls` entries take precedence. A complete example is in [values-all-workers-agent-fs.yaml](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/examples/v - Network accessline 52
A complete example is in [values-all-workers-agent-fs.yaml](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/examples/values-all-workers-agent-fs.yaml). - Network accessline 52
A complete example is in [values-all-workers-agent-fs.yaml](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/examples/values-all-workers-agent-fs.yaml). - Network accessline 60
config: publicMcpBaseUrl: https://swarm-api.example.com - Network accessline 60
config: publicMcpBaseUrl: https://swarm-api.example.com - Network accessline 61
publicMcpBaseUrl: https://swarm-api.example.com - Network accessline 61
publicMcpBaseUrl: https://swarm-api.example.com - Network accessline 64
An empty `ingress.tls` with no issuer derives an `http://` public URL. Set `config.publicMcpBaseUrl` whenever TLS is not visible to the chart. - Network accessline 64
An empty `ingress.tls` with no issuer derives an `http://` public URL. Set `config.publicMcpBaseUrl` whenever TLS is not visible to the chart. - Network accessline 69
curl -fsS https://swarm-api.example.com/health - Network accessline 69
curl -fsS https://swarm-api.example.com/health - Network accessline 70
curl -fsS https://swarm-files.example.com/health - Network accessline 70
curl -fsS https://swarm-files.example.com/health - Network accessline 73
Open `https://app.agent-swarm.dev`, enter the API URL and key, and confirm the agent list loads without a mixed-content or CORS error. - Network accessline 73
Open `https://app.agent-swarm.dev`, enter the API URL and key, and confirm the agent list loads without a mixed-content or CORS error.
skills/agent-swarm/references/operate-k8s.md
- Network accessline 3
Day-2 procedures for a chart release named `swarm` in namespace `agent-swarm`. Adjust names when you used a different release or `fullnameOverride`. Re-fetch the [chart README](https://github.com/desplega-ai/agent-swarm/blob/main/charts/age - Network accessline 3
Day-2 procedures for a chart release named `swarm` in namespace `agent-swarm`. Adjust names when you used a different release or `fullnameOverride`. Re-fetch the [chart README](https://github.com/desplega-ai/agent-swarm/blob/main/charts/age - Network accessline 4
Re-fetch the [chart README](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md) and [values](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/values.yaml) before acting. - Network accessline 4
Re-fetch the [chart README](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md) and [values](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/values.yaml) before acting. - Access to secretsline 14
[Credential-related source omitted] - Access to secretsline 14
[Credential-related source omitted] - Network accessline 21
kubectl -n agent-swarm get pods,pvc,ingress,certificate kubectl -n agent-swarm logs statefulset/swarm-agent-swarm-api --tail=100 curl -fsS https://swarm-api.example.com/health - Network accessline 21
kubectl -n agent-swarm get pods,pvc,ingress,certificate kubectl -n agent-swarm logs statefulset/swarm-agent-swarm-api --tail=100 curl -fsS https://swarm-api.example.com/health - Network accessline 22
[Credential-related source omitted] - Network accessline 22
[Credential-related source omitted] - Network accessline 23
curl -fsS https://swarm-api.example.com/health - Network accessline 23
curl -fsS https://swarm-api.example.com/health - Network accessline 24
[Credential-related source omitted] - Network accessline 24
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Network accessline 27
Pool pods have no HTTP listener. Their probes run `pgrep -f agent-swarm`. Read pool logs with `kubectl -n agent-swarm logs swarm-agent-swarm-coder-0`. Confirm `PUBLIC_MCP_BASE_URL` in the ConfigMap is the `https://` origin browsers use. Rea - Network accessline 27
Pool pods have no HTTP listener. Their probes run `pgrep -f agent-swarm`. Read pool logs with `kubectl -n agent-swarm logs swarm-agent-swarm-coder-0`. Confirm `PUBLIC_MCP_BASE_URL` in the ConfigMap is the `https://` origin browsers use. Rea - Network accessline 28
Confirm `PUBLIC_MCP_BASE_URL` in the ConfigMap is the `https://` origin browsers use. Read the [HTTPS procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/https.md). - Network accessline 28
Confirm `PUBLIC_MCP_BASE_URL` in the ConfigMap is the `https://` origin browsers use. Read the [HTTPS procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/https.md). - Network accessline 65
Never change `SECRETS_ENCRYPTION_KEY`. Every encrypted swarm-config value (integration tokens, agent-fs keys) becomes unreadable. Read [secrets encryption](https://docs.agent-swarm.dev/docs/guides/secrets-encryption). - Network accessline 65
Never change `SECRETS_ENCRYPTION_KEY`. Every encrypted swarm-config value (integration tokens, agent-fs keys) becomes unreadable. Read [secrets encryption](https://docs.agent-swarm.dev/docs/guides/secrets-encryption). - Network accessline 69
Litestream streams the SQLite WAL to S3 when `litestream.enabled` is set. Configure it in the [chart README](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md). Restoration follows the [Litestream guide](http - Network accessline 69
Litestream streams the SQLite WAL to S3 when `litestream.enabled` is set. Configure it in the [chart README](https://github.com/desplega-ai/agent-swarm/blob/main/charts/agent-swarm/README.md). Restoration follows the [Litestream guide](http - Network accessline 90
| Pool logs `credential-wait` | Secret has no harness credential | Add `CLAUDE_CODE_OAUTH_TOKEN` (or the provider's key) to the Secret and restart. | | Ingress returns 502 or LB targets unhealthy | Probe path | Load balancers must probe `/h - Network accessline 90
| Pool logs `credential-wait` | Secret has no harness credential | Add `CLAUDE_CODE_OAUTH_TOKEN` (or the provider's key) to the Secret and restart. | | Ingress returns 502 or LB targets unhealthy | Probe path | Load balancers must probe `/h - Network accessline 91
| Ingress returns 502 or LB targets unhealthy | Probe path | Load balancers must probe `/health`; `/` returns 401. See the chart README "Load balancer health checks". | | Dashboard shows mixed-content or CORS error | `PUBLIC_MCP_BASE_URL` a - Network accessline 91
| Ingress returns 502 or LB targets unhealthy | Probe path | Load balancers must probe `/health`; `/` returns 401. See the chart README "Load balancer health checks". | | Dashboard shows mixed-content or CORS error | `PUBLIC_MCP_BASE_URL` a - Network accessline 92
| Dashboard shows mixed-content or CORS error | `PUBLIC_MCP_BASE_URL` and `CORS_ALLOWED_ORIGINS` | Public URL must be `https://`. Self-hosted UI origins go in `CORS_ALLOWED_ORIGINS` via `config.extraEnv`. Read the [Kubernetes guide](https:/ - Network accessline 92
| Dashboard shows mixed-content or CORS error | `PUBLIC_MCP_BASE_URL` and `CORS_ALLOWED_ORIGINS` | Public URL must be `https://`. Self-hosted UI origins go in `CORS_ALLOWED_ORIGINS` via `config.extraEnv`. Read the [Kubernetes guide](https:/ - Network accessline 93
| `certificate` stays `READY=False` | `kubectl describe certificate`, `kubectl get challenge -A` | HTTP-01 needs port 80 reachable at the host, DNS pointing at the ingress, and a matching `ingressClassName` in the issuer. | | agent-fs stays - Network accessline 93
| `certificate` stays `READY=False` | `kubectl describe certificate`, `kubectl get challenge -A` | HTTP-01 needs port 80 reachable at the host, DNS pointing at the ingress, and a matching `ingressClassName` in the issuer. | | agent-fs stays - Network accessline 94
[Credential-related source omitted] - Network accessline 94
[Credential-related source omitted] - Access to secretsline 94
[Credential-related source omitted] - Access to secretsline 94
[Credential-related source omitted] - Network accessline 101
kubectl -n agent-swarm port-forward service/swarm-agent-swarm-api 3013:3013 curl -fsS http://localhost:3013/health - Network accessline 101
kubectl -n agent-swarm port-forward service/swarm-agent-swarm-api 3013:3013 curl -fsS http://localhost:3013/health - Network accessline 102
curl -fsS http://localhost:3013/health - Network accessline 102
curl -fsS http://localhost:3013/health
skills/agent-swarm/references/slack.md
- Network accessline 3
Slack uses Socket Mode, so it does not need a public webhook URL. Re-fetch the [manifest](https://github.com/desplega-ai/agent-swarm/blob/main/slack-manifest.json) and [Slack guide](https://docs.agent-swarm.dev/docs/integrations/slack). - Network accessline 3
Slack uses Socket Mode, so it does not need a public webhook URL. Re-fetch the [manifest](https://github.com/desplega-ai/agent-swarm/blob/main/slack-manifest.json) and [Slack guide](https://docs.agent-swarm.dev/docs/integrations/slack). - Network accessline 4
Re-fetch the [manifest](https://github.com/desplega-ai/agent-swarm/blob/main/slack-manifest.json) and [Slack guide](https://docs.agent-swarm.dev/docs/integrations/slack). - Network accessline 4
Re-fetch the [manifest](https://github.com/desplega-ai/agent-swarm/blob/main/slack-manifest.json) and [Slack guide](https://docs.agent-swarm.dev/docs/integrations/slack). - Network accessline 6
1. Create a Slack app from a manifest at `https://api.slack.com/apps`. 2. Import the current `slack-manifest.json`. It supplies scopes, bot events, Socket Mode, Interactivity, and Agent View. - Network accessline 6
1. Create a Slack app from a manifest at `https://api.slack.com/apps`. 2. Import the current `slack-manifest.json`. It supplies scopes, bot events, Socket Mode, Interactivity, and Agent View. - Access to secretsline 12
[Credential-related source omitted] - Access to secretsline 12
[Credential-related source omitted] - Network accessline 16
curl -fsS https://raw.githubusercontent.com/desplega-ai/agent-swarm/main/slack-manifest.json \ - Network accessline 16
curl -fsS https://raw.githubusercontent.com/desplega-ai/agent-swarm/main/slack-manifest.json \ - Network accessline 17
-o /tmp/slack-manifest.json jq -n '{scope:"global",key:"SLACK_BOT_TOKEN",value:env.SLACK_BOT_TOKEN,isSecret:true}' \ | curl -fsS -X PUT "$MCP_BASE_URL/api/config" \ - Network accessline 17
-o /tmp/slack-manifest.json jq -n '{scope:"global",key:"SLACK_BOT_TOKEN",value:env.SLACK_BOT_TOKEN,isSecret:true}' \ | curl -fsS -X PUT "$MCP_BASE_URL/api/config" \ - Network accessline 18
[Credential-related source omitted] - Network accessline 18
[Credential-related source omitted] - Access to secretsline 18
[Credential-related source omitted] - Access to secretsline 18
[Credential-related source omitted] - Network accessline 19
| curl -fsS -X PUT "$MCP_BASE_URL/api/config" \ - Network accessline 19
| curl -fsS -X PUT "$MCP_BASE_URL/api/config" \ - Access to secretsline 20
[Credential-related source omitted] - Access to secretsline 20
[Credential-related source omitted] - Network accessline 21
[Credential-related source omitted] - Network accessline 21
[Credential-related source omitted] - Access to secretsline 21
[Credential-related source omitted] - Access to secretsline 21
[Credential-related source omitted] - Network accessline 22
| curl -fsS -X PUT "$MCP_BASE_URL/api/config" \ - Network accessline 22
| curl -fsS -X PUT "$MCP_BASE_URL/api/config" \ - Network accessline 23
[Credential-related source omitted] - Network accessline 23
[Credential-related source omitted] - Access to secretsline 23
[Credential-related source omitted] - Access to secretsline 23
[Credential-related source omitted] - Network accessline 24
[Credential-related source omitted] - Network accessline 24
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Network accessline 25
[Credential-related source omitted] - Network accessline 25
[Credential-related source omitted] - Access to secretsline 25
[Credential-related source omitted] - Access to secretsline 25
[Credential-related source omitted] - Network accessline 26
[Credential-related source omitted] - Network accessline 26
[Credential-related source omitted] - Network accessline 27
[Credential-related source omitted] - Network accessline 27
[Credential-related source omitted] - Access to secretsline 27
[Credential-related source omitted] - Access to secretsline 27
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 39
[Credential-related source omitted] - Access to secretsline 39
[Credential-related source omitted] - Network accessline 44
Send the bot a DM: `Say hello and report which workers are online.` Confirm that a task appears in the UI and the bot replies. For channel work, invite the bot and mention it. Read the [integration configuration code](https://github.com/des - Network accessline 44
Send the bot a DM: `Say hello and report which workers are online.` Confirm that a task appears in the UI and the bot replies. For channel work, invite the bot and mention it. Read the [integration configuration code](https://github.com/des - Network accessline 46
Read the [integration configuration code](https://github.com/desplega-ai/agent-swarm/blob/main/src/http/core.ts) for reload behavior. - Network accessline 46
Read the [integration configuration code](https://github.com/desplega-ai/agent-swarm/blob/main/src/http/core.ts) for reload behavior.
skills/agent-swarm/references/upgrade.md
- Network accessline 3
Applies to Compose. For Kubernetes, the chart already pins and its day-2 upgrade steps are in the [Kubernetes operations procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/operate-k8s.md). - Network accessline 3
Applies to Compose. For Kubernetes, the chart already pins and its day-2 upgrade steps are in the [Kubernetes operations procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/operate-k8s.md). - Access to secretsline 15
[Credential-related source omitted] - Access to secretsline 15
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Network accessline 40
The Compose example sets `pull_policy: always`, so an unpinned deployment can move to a newer build on any `up -d` or container restart — including a restart you did not intend as an upgrade. The API applies SQL migrations at boot. When the - Network accessline 40
The Compose example sets `pull_policy: always`, so an unpinned deployment can move to a newer build on any `up -d` or container restart — including a restart you did not intend as an upgrade. The API applies SQL migrations at boot. When the - Network accessline 42
Pin the API and every agent service to the same published release. Read the [releases](https://github.com/desplega-ai/agent-swarm/releases). - Network accessline 42
Pin the API and every agent service to the same published release. Read the [releases](https://github.com/desplega-ai/agent-swarm/releases). - Network accessline 46
One variable drives the API and all agent services in the [Compose example](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml). Set it in `.env`: - Network accessline 46
One variable drives the API and all agent services in the [Compose example](https://github.com/desplega-ai/agent-swarm/blob/main/docker-compose.example.yml). Set it in `.env`: - Access to secretsline 53
[Credential-related source omitted] - Access to secretsline 53
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Network accessline 73
Stopping the API first gives a consistent SQLite copy. Copy the whole directory so the WAL sidecars and `.page-session-secret` come with it. Store the backup and the encryption key together and off the host; an encrypted database without it - Network accessline 73
Stopping the API first gives a consistent SQLite copy. Copy the whole directory so the WAL sidecars and `.page-session-secret` come with it. Store the backup and the encryption key together and off the host; an encrypted database without it - Access to secretsline 79
[Credential-related source omitted] - Access to secretsline 79
[Credential-related source omitted] - Access to secretsline 80
[Credential-related source omitted] - Access to secretsline 80
[Credential-related source omitted] - Network accessline 83
1. Read the release notes between your pinned version and the target. Check [releases](https://github.com/desplega-ai/agent-swarm/releases) and re-read the [environment example](https://github.com/desplega-ai/agent-swarm/blob/main/.env.dock - Network accessline 83
1. Read the release notes between your pinned version and the target. Check [releases](https://github.com/desplega-ai/agent-swarm/releases) and re-read the [environment example](https://github.com/desplega-ai/agent-swarm/blob/main/.env.dock - Access to secretsline 89
[Credential-related source omitted] - Access to secretsline 89
[Credential-related source omitted] - Access to secretsline 90
[Credential-related source omitted] - Access to secretsline 90
[Credential-related source omitted] - Access to secretsline 91
[Credential-related source omitted] - Access to secretsline 91
[Credential-related source omitted] - Access to secretsline 100
[Credential-related source omitted] - Access to secretsline 100
[Credential-related source omitted] - Network accessline 108
curl -fsS "$MCP_BASE_URL/health" - Network accessline 108
curl -fsS "$MCP_BASE_URL/health" - Network accessline 111
Then submit a task and read its result to completion with the [API verification procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/usage.md). A completed task with output is the passing signal. - Network accessline 111
Then submit a task and read its result to completion with the [API verification procedure](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/usage.md). A completed task with output is the passing signal. - Access to secretsline 115
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Network accessline 127
Restore the database and the encryption key as a pair. Read [component minimums](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/components.md) for what else must be preserved. - Network accessline 127
Restore the database and the encryption key as a pair. Read [component minimums](https://github.com/desplega-ai/agent-swarm/blob/main/skills/agent-swarm/references/components.md) for what else must be preserved.
skills/agent-swarm/references/usage.md
- Network accessline 3
Re-fetch the [HTTP schema](https://github.com/desplega-ai/agent-swarm/blob/main/openapi.json) and [CLI help source](https://github.com/desplega-ai/agent-swarm/blob/main/src/cli.tsx). - Network accessline 3
Re-fetch the [HTTP schema](https://github.com/desplega-ai/agent-swarm/blob/main/openapi.json) and [CLI help source](https://github.com/desplega-ai/agent-swarm/blob/main/src/cli.tsx). - Access to secretsline 7
[Credential-related source omitted] - Access to secretsline 7
[Credential-related source omitted] - Network accessline 11
export MCP_BASE_URL=http://localhost:3013 curl -fsS "$MCP_BASE_URL/health" - Network accessline 11
export MCP_BASE_URL=http://localhost:3013 curl -fsS "$MCP_BASE_URL/health" - Network accessline 12
curl -fsS "$MCP_BASE_URL/health" - Network accessline 12
curl -fsS "$MCP_BASE_URL/health" - Network accessline 13
curl -fsS "$MCP_BASE_URL/openapi.json" -o /tmp/swarm-openapi.json - Network accessline 13
curl -fsS "$MCP_BASE_URL/openapi.json" -o /tmp/swarm-openapi.json - Network accessline 14
[Credential-related source omitted] - Network accessline 14
[Credential-related source omitted] - Access to secretsline 14
[Credential-related source omitted] - Access to secretsline 14
[Credential-related source omitted] - Network accessline 15
[Credential-related source omitted] - Network accessline 15
[Credential-related source omitted] - Network accessline 16
[Credential-related source omitted] - Network accessline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Network accessline 18
[Credential-related source omitted] - Network accessline 18
[Credential-related source omitted] - Network accessline 20
[Credential-related source omitted] - Network accessline 20
[Credential-related source omitted] - Access to secretsline 20
[Credential-related source omitted] - Access to secretsline 20
[Credential-related source omitted] - Network accessline 24
If it fails, inspect its failure reason and worker status before submitting another task. The API serves interactive documentation at `/docs`. The task POST returns the task directly. The agent list uses an `agents` envelope. When RBAC is e - Network accessline 24
If it fails, inspect its failure reason and worker status before submitting another task. The API serves interactive documentation at `/docs`. The task POST returns the task directly. The agent list uses an `agents` envelope. When RBAC is e - Network accessline 26
When RBAC is enabled, use credentials with permission to create tasks. See the [API reference](https://docs.agent-swarm.dev/docs/api-reference). - Network accessline 26
When RBAC is enabled, use credentials with permission to create tasks. See the [API reference](https://docs.agent-swarm.dev/docs/api-reference). - Access to secretsline 30
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Network accessline 40
To make your coding agent the lead, ask it to call `join-swarm` with `lead: true` and a name. Use lead registration only if the deployment has no existing lead. Do not create a second lead beside the Compose or Helm lead. Read the [registra - Network accessline 40
To make your coding agent the lead, ask it to call `join-swarm` with `lead: true` and a name. Use lead registration only if the deployment has no existing lead. Do not create a second lead beside the Compose or Helm lead. Read the [registra - Network accessline 42
Read the [registration tool](https://github.com/desplega-ai/agent-swarm/blob/main/src/tools/join-swarm.ts) before choosing the role. - Network accessline 42
Read the [registration tool](https://github.com/desplega-ai/agent-swarm/blob/main/src/tools/join-swarm.ts) before choosing the role. - Network accessline 44
[Credential-related source omitted] - Network accessline 44
[Credential-related source omitted] - Network accessline 45
An agent client also supplies a stable UUID in `X-Agent-ID`. Read [getting started](https://docs.agent-swarm.dev/docs/getting-started). - Network accessline 45
An agent client also supplies a stable UUID in `X-Agent-ID`. Read [getting started](https://docs.agent-swarm.dev/docs/getting-started). - Network accessline 49
Open `https://app.agent-swarm.dev` and configure a connection to your API with its key. - Network accessline 49
Open `https://app.agent-swarm.dev` and configure a connection to your API with its key. - Network accessline 58
Use the URL printed by the development server. Configure its API connection in the UI. The UI manages agents, tasks, integrations, secrets, and configuration. Read the [UI guide](https://docs.agent-swarm.dev/docs/ui). - Network accessline 58
Use the URL printed by the development server. Configure its API connection in the UI. The UI manages agents, tasks, integrations, secrets, and configuration. Read the [UI guide](https://docs.agent-swarm.dev/docs/ui). - Network accessline 59
The UI manages agents, tasks, integrations, secrets, and configuration. Read the [UI guide](https://docs.agent-swarm.dev/docs/ui). - Network accessline 59
The UI manages agents, tasks, integrations, secrets, and configuration. Read the [UI guide](https://docs.agent-swarm.dev/docs/ui).
templates/community/open-prompt-showreel/skills/motion-design-replication/SKILL.md
- Network accessline 26
- **Mark**: `apps/ui/public/logo.png` in `desplega-ai/agent-swarm` (the hex mark; byte-identical to `docs-site/public/logo.png` and `https://agent-swarm.dev/logo.png`; verify with `sha256sum`). There is no logo SVG.
templates/community/open-prompt-showreel/skills/motion-design-video-analysis/SKILL.md
- Access to secretsline 18
[Credential-related source omitted] - Network accessline 58
Only when the user asks which model to use, or the default call fails twice. Resolve IDs from the live catalogue (`GET https://openrouter.ai/api/v1/models`, filter `architecture.input_modalities` for `image`/`video`; users' remembered names
templates/community/open-prompt-showreel/skills/open-prompt-showreel/SKILL.md
- Network accessline 97
- Agent Swarm logo = `apps/ui/public/logo.png` on origin/main: a solid gold hexagon inside a lighter gold honeycomb. It is byte-identical to `docs-site/public/logo.png` and `https://agent-swarm.dev/logo.png`. Check the sha256 against the li - Network accessline 104
- License: CC0 or CC BY only. No NC (company post), no ND (we cut and stretch it), no SA (it would carry over to the video). `fetch-music.sh` enforces an allowlist (CC0 1.0, CC BY 1.0-4.0); read the license on the source page yourself. Sour
templates/community/open-prompt-showreel/skills/video-generation/SKILL.md
- Network accessline 14
1. **Remotion for repo-committed video.** `npx remotion studio` for previews, `remotion render` for mp4s. For a one-off design-led cut with no repo, use `open-prompt-showreel` instead. 2. **Ask for audio, don't pick it.** Music is a brand c - Network accessline 15
2. **Ask for audio, don't pick it.** Music is a brand call. A person on the team chooses the track (CC0 or CC BY 4.0, for example from https://freesound.org). Never grab something yourself; ask. There is no default bed. - Dangerous shell operationline 71
sudo apt-get install -y ffmpeg libnspr4 libnss3 libatk1.0-0 libatk-bridge2.0-0 \ - Network accessline 137
- Put attribution in `<video-project>/README.md` with artist, source URL and license, for example: > _Track title_ by **Artist** (https://freesound.org/s/<id>/), License: [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) - Network accessline 138
> _Track title_ by **Artist** (https://freesound.org/s/<id>/), License: [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) - Network accessline 168
<video src="https://github.com/<org>/<repo>/raw/main/assets/<name>.mp4"
templates/skills/agent-browser/SKILL.md
- Network accessline 43
- Re-run `snapshot` after every navigation or state change. Refs are only valid for the snapshot that produced them. - Run one browser session at a time. Call `store-progress` between page batches so the heartbeat watchdog sees you. - The b - Network accessline 44
- Run one browser session at a time. Call `store-progress` between page batches so the heartbeat watchdog sees you. - The browser is headless. Local servers inside the worker container are reachable at `http://localhost:<port>`. - The image - Network accessline 45
- The browser is headless. Local servers inside the worker container are reachable at `http://localhost:<port>`. - Network accessline 81
- **GitHub PR body or comment**: upload the PNG, GIF or mp4 as a GitHub user attachment with the `github-attach` skill and embed ``. Attachments never expire and mp4s play inline.
templates/skills/agent-browser/content.md
- Network accessline 38
- Re-run `snapshot` after every navigation or state change. Refs are only valid for the snapshot that produced them. - Run one browser session at a time. Call `store-progress` between page batches so the heartbeat watchdog sees you. - The b - Network accessline 39
- Run one browser session at a time. Call `store-progress` between page batches so the heartbeat watchdog sees you. - The browser is headless. Local servers inside the worker container are reachable at `http://localhost:<port>`. - The image - Network accessline 40
- The browser is headless. Local servers inside the worker container are reachable at `http://localhost:<port>`. - Network accessline 76
- **GitHub PR body or comment**: upload the PNG, GIF or mp4 as a GitHub user attachment with the `github-attach` skill and embed ``. Attachments never expire and mp4s play inline.
templates/skills/agentmail-sending/SKILL.md
- Network accessline 1
--- name: agentmail-sending description: Canonical AgentMail send-message API reference for swarm agents. Pins the base URL, required field names, text-only rendering workaround, BCC policy, and ready-to-copy curl / swarm-script examples so - Network accessline 2
name: agentmail-sending description: Canonical AgentMail send-message API reference for swarm agents. Pins the base URL, required field names, text-only rendering workaround, BCC policy, and ready-to-copy curl / swarm-script examples so age - Network accessline 3
description: Canonical AgentMail send-message API reference for swarm agents. Pins the base URL, required field names, text-only rendering workaround, BCC policy, and ready-to-copy curl / swarm-script examples so agents do not rediscover th - Network accessline 14
https://api.agentmail.to/v0/ - Network accessline 47
https://api.agentmail.to/v0/inboxes/{inbox}/messages/send - Network accessline 53
[Credential-related source omitted] - Access to secretsline 53
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Access to secretsline 68
[Credential-related source omitted] - Access to secretsline 94
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Network accessline 99
[Credential-related source omitted] - Network accessline 100
const response = await ctx.stdlib.fetch( - Network accessline 101
\`https://api.agentmail.to/v0/inboxes/\${encodeURIComponent(args.inbox)}/messages/send\`, - Network accessline 154
- Use `https://api.agentmail.to/v0/`. - Access to secretsline 168
[Credential-related source omitted]
templates/skills/agentmail-sending/config.json
- Network accessline 5
"slug": "agentmail-sending", "title": "AgentMail Sending", "description": "Canonical AgentMail send-message API reference for swarm agents. Pins the base URL, required field names, text-only rendering workaround, BCC policy, and ready-t - Network accessline 6
"title": "AgentMail Sending", "description": "Canonical AgentMail send-message API reference for swarm agents. Pins the base URL, required field names, text-only rendering workaround, BCC policy, and ready-to-copy curl / swarm-script exam - Network accessline 7
"description": "Canonical AgentMail send-message API reference for swarm agents. Pins the base URL, required field names, text-only rendering workaround, BCC policy, and ready-to-copy curl / swarm-script examples so agents do not rediscover
templates/skills/agentmail-sending/content.md
- Network accessline 9
https://api.agentmail.to/v0/ - Network accessline 42
https://api.agentmail.to/v0/inboxes/{inbox}/messages/send - Network accessline 48
[Credential-related source omitted] - Access to secretsline 48
[Credential-related source omitted] - Access to secretsline 49
[Credential-related source omitted] - Access to secretsline 63
[Credential-related source omitted] - Access to secretsline 89
[Credential-related source omitted] - Access to secretsline 91
[Credential-related source omitted] - Network accessline 94
[Credential-related source omitted] - Network accessline 95
const response = await ctx.stdlib.fetch( - Network accessline 96
\`https://api.agentmail.to/v0/inboxes/\${encodeURIComponent(args.inbox)}/messages/send\`, - Network accessline 149
- Use `https://api.agentmail.to/v0/`. - Access to secretsline 163
[Credential-related source omitted]
templates/skills/attio-interaction/SKILL.md
- Network accessline 13
[Credential-related source omitted] - Access to secretsline 13
[Credential-related source omitted] - Network accessline 14
2. Base URL: `https://api.attio.com/v2/` - Access to secretsline 15
[Credential-related source omitted] - Access to secretsline 23
[Credential-related source omitted] - Network accessline 25
[Credential-related source omitted] - Access to secretsline 25
[Credential-related source omitted] - Access to secretsline 26
[Credential-related source omitted] - Network accessline 47
[Credential-related source omitted] - Access to secretsline 47
[Credential-related source omitted] - Access to secretsline 48
[Credential-related source omitted] - Network accessline 56
[Credential-related source omitted] - Access to secretsline 56
[Credential-related source omitted] - Access to secretsline 57
[Credential-related source omitted] - Network accessline 73
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Network accessline 84
[Credential-related source omitted] - Access to secretsline 84
[Credential-related source omitted] - Access to secretsline 85
[Credential-related source omitted] - Network accessline 102
[Credential-related source omitted] - Access to secretsline 102
[Credential-related source omitted] - Access to secretsline 103
[Credential-related source omitted] - Network accessline 122
[Credential-related source omitted] - Access to secretsline 122
[Credential-related source omitted] - Access to secretsline 123
[Credential-related source omitted] - Network accessline 140
[Credential-related source omitted] - Access to secretsline 140
[Credential-related source omitted] - Access to secretsline 141
[Credential-related source omitted] - Network accessline 156
[Credential-related source omitted] - Access to secretsline 156
[Credential-related source omitted] - Access to secretsline 157
[Credential-related source omitted] - Network accessline 161
[Credential-related source omitted] - Access to secretsline 161
[Credential-related source omitted] - Access to secretsline 162
[Credential-related source omitted] - Network accessline 181
[Credential-related source omitted] - Access to secretsline 181
[Credential-related source omitted] - Access to secretsline 182
[Credential-related source omitted] - Network accessline 197
[Credential-related source omitted] - Access to secretsline 197
[Credential-related source omitted] - Access to secretsline 198
[Credential-related source omitted] - Network accessline 202
[Credential-related source omitted] - Access to secretsline 202
[Credential-related source omitted] - Access to secretsline 203
[Credential-related source omitted] - Network accessline 212
[Credential-related source omitted] - Access to secretsline 212
[Credential-related source omitted] - Access to secretsline 213
[Credential-related source omitted] - Access to secretsline 247
[Credential-related source omitted] - Access to secretsline 263
[Credential-related source omitted] - Network accessline 265
[Credential-related source omitted] - Access to secretsline 265
[Credential-related source omitted] - Access to secretsline 266
[Credential-related source omitted] - Network accessline 270
echo "$DEALS" | jq -r '.data[] | .id.record_id' | while read -r RECORD_ID; do RECORD=$(curl -sS "https://api.attio.com/v2/objects/deals/records/$RECORD_ID" \ - Network accessline 271
[Credential-related source omitted] - Access to secretsline 271
[Credential-related source omitted] - Access to secretsline 272
[Credential-related source omitted] - Network accessline 281
- Official Attio REST API docs: https://developers.attio.com/reference - Network accessline 282
- Official Attio MCP overview: https://docs.attio.com/mcp/overview
templates/skills/attio-interaction/config.json
- Access to secretsline 10
[Credential-related source omitted]
templates/skills/attio-interaction/content.md
- Network accessline 7
[Credential-related source omitted] - Access to secretsline 7
[Credential-related source omitted] - Network accessline 8
2. Base URL: `https://api.attio.com/v2/` - Access to secretsline 9
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Network accessline 19
[Credential-related source omitted] - Access to secretsline 19
[Credential-related source omitted] - Access to secretsline 20
[Credential-related source omitted] - Network accessline 41
[Credential-related source omitted] - Access to secretsline 41
[Credential-related source omitted] - Access to secretsline 42
[Credential-related source omitted] - Network accessline 50
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Access to secretsline 51
[Credential-related source omitted] - Network accessline 67
[Credential-related source omitted] - Access to secretsline 67
[Credential-related source omitted] - Access to secretsline 68
[Credential-related source omitted] - Network accessline 78
[Credential-related source omitted] - Access to secretsline 78
[Credential-related source omitted] - Access to secretsline 79
[Credential-related source omitted] - Network accessline 96
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Access to secretsline 97
[Credential-related source omitted] - Network accessline 116
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted] - Access to secretsline 117
[Credential-related source omitted] - Network accessline 134
[Credential-related source omitted] - Access to secretsline 134
[Credential-related source omitted] - Access to secretsline 135
[Credential-related source omitted] - Network accessline 150
[Credential-related source omitted] - Access to secretsline 150
[Credential-related source omitted] - Access to secretsline 151
[Credential-related source omitted] - Network accessline 155
[Credential-related source omitted] - Access to secretsline 155
[Credential-related source omitted] - Access to secretsline 156
[Credential-related source omitted] - Network accessline 175
[Credential-related source omitted] - Access to secretsline 175
[Credential-related source omitted] - Access to secretsline 176
[Credential-related source omitted] - Network accessline 191
[Credential-related source omitted] - Access to secretsline 191
[Credential-related source omitted] - Access to secretsline 192
[Credential-related source omitted] - Network accessline 196
[Credential-related source omitted] - Access to secretsline 196
[Credential-related source omitted] - Access to secretsline 197
[Credential-related source omitted] - Network accessline 206
[Credential-related source omitted] - Access to secretsline 206
[Credential-related source omitted] - Access to secretsline 207
[Credential-related source omitted] - Access to secretsline 241
[Credential-related source omitted] - Access to secretsline 257
[Credential-related source omitted] - Network accessline 259
[Credential-related source omitted] - Access to secretsline 259
[Credential-related source omitted] - Access to secretsline 260
[Credential-related source omitted] - Network accessline 264
echo "$DEALS" | jq -r '.data[] | .id.record_id' | while read -r RECORD_ID; do RECORD=$(curl -sS "https://api.attio.com/v2/objects/deals/records/$RECORD_ID" \ - Network accessline 265
[Credential-related source omitted] - Access to secretsline 265
[Credential-related source omitted] - Access to secretsline 266
[Credential-related source omitted] - Network accessline 275
- Official Attio REST API docs: https://developers.attio.com/reference - Network accessline 276
- Official Attio MCP overview: https://docs.attio.com/mcp/overview
templates/skills/composio/SKILL.md
- Access to secretsline 15
[Credential-related source omitted] - Network accessline 114
agent-swarm x composio POST /connected_accounts/link \ --body '{"auth_config_id":"<auth-config-id>","user_id":"<connected-account-email>"}' # → returns { redirect_url / connect_url: "https://connect.composio.dev/link/lk_…" } - Network accessline 116
# → returns { redirect_url / connect_url: "https://connect.composio.dev/link/lk_…" }
templates/skills/composio/config.json
- Access to secretsline 10
[Credential-related source omitted]
templates/skills/composio/content.md
- Access to secretsline 10
[Credential-related source omitted] - Network accessline 109
agent-swarm x composio POST /connected_accounts/link \ --body '{"auth_config_id":"<auth-config-id>","user_id":"<connected-account-email>"}' # → returns { redirect_url / connect_url: "https://connect.composio.dev/link/lk_…" } - Network accessline 111
# → returns { redirect_url / connect_url: "https://connect.composio.dev/link/lk_…" }
templates/skills/kapso-whatsapp/SKILL.md
- Network accessline 9
Kapso (https://kapso.ai) is a WhatsApp platform vendor that fronts the Meta Cloud API. A swarm provisions one or more WhatsApp phone numbers and wires each one to either the native inbound handler or a workflow that dispatches a task per in - Network accessline 37
| Key | Value | |---|---| | `KAPSO_API_BASE_URL` | `https://api.kapso.ai` (host only, no `/platform/v1`) | - Network accessline 38
|---|---| | `KAPSO_API_BASE_URL` | `https://api.kapso.ai` (host only, no `/platform/v1`) | | `KAPSO_API_KEY` | API key (`X-API-Key` header) | - Network accessline 39
| `KAPSO_API_BASE_URL` | `https://api.kapso.ai` (host only, no `/platform/v1`) | - Access to secretsline 40
[Credential-related source omitted] - Network accessline 44
[Credential-related source omitted] - Access to secretsline 44
[Credential-related source omitted] - Network accessline 47
# Values from the `get-config` MCP tool (key:<NAME> includeSecrets:true): API_BASE=https://api.kapso.ai # KAPSO_API_BASE_URL - Network accessline 48
API_BASE=https://api.kapso.ai # KAPSO_API_BASE_URL - Access to secretsline 49
[Credential-related source omitted] - Network accessline 56
git clone --depth=1 https://github.com/gokapso/agent-skills /tmp/kapso-skills - Network accessline 135
[Credential-related source omitted] - Access to secretsline 135
[Credential-related source omitted] - Network accessline 137
# → { "url": "https://lookaside.fbsbx.com/...", "mime_type": "...", "file_size": ..., "id": "...", "sha256": "..." } - Network accessline 141
[Credential-related source omitted] - Access to secretsline 141
[Credential-related source omitted] - Network accessline 168
Use the Kapso platform endpoints via curl (no CLI needed): - Access to secretsline 172
[Credential-related source omitted] - Network accessline 174
[Credential-related source omitted] - Network accessline 175
[Credential-related source omitted] - Access to secretsline 175
[Credential-related source omitted] - Network accessline 178
[Credential-related source omitted] - Network accessline 179
[Credential-related source omitted] - Access to secretsline 179
[Credential-related source omitted] - Network accessline 182
[Credential-related source omitted] - Network accessline 183
[Credential-related source omitted] - Network accessline 184
[Credential-related source omitted] - Access to secretsline 184
[Credential-related source omitted] - Network accessline 187
[Credential-related source omitted] - Network accessline 188
[Credential-related source omitted] - Access to secretsline 188
[Credential-related source omitted] - Network accessline 204
[Credential-related source omitted] - Access to secretsline 204
[Credential-related source omitted] - Network accessline 241
[Credential-related source omitted] - Access to secretsline 241
[Credential-related source omitted] - Network accessline 291
[Credential-related source omitted] - Access to secretsline 291
[Credential-related source omitted] - Network accessline 307
[Credential-related source omitted] - Access to secretsline 307
[Credential-related source omitted] - Network accessline 325
[Credential-related source omitted] - Access to secretsline 325
[Credential-related source omitted] - Access to secretsline 347
[Credential-related source omitted]
templates/skills/kapso-whatsapp/config.json
- Access to secretsline 11
[Credential-related source omitted]
templates/skills/kapso-whatsapp/content.md
- Network accessline 4
Kapso (https://kapso.ai) is a WhatsApp platform vendor that fronts the Meta Cloud API. A swarm provisions one or more WhatsApp phone numbers and wires each one to either the native inbound handler or a workflow that dispatches a task per in - Network accessline 32
| Key | Value | |---|---| | `KAPSO_API_BASE_URL` | `https://api.kapso.ai` (host only, no `/platform/v1`) | - Network accessline 33
|---|---| | `KAPSO_API_BASE_URL` | `https://api.kapso.ai` (host only, no `/platform/v1`) | | `KAPSO_API_KEY` | API key (`X-API-Key` header) | - Network accessline 34
| `KAPSO_API_BASE_URL` | `https://api.kapso.ai` (host only, no `/platform/v1`) | - Access to secretsline 35
[Credential-related source omitted] - Network accessline 39
[Credential-related source omitted] - Access to secretsline 39
[Credential-related source omitted] - Network accessline 42
# Values from the `get-config` MCP tool (key:<NAME> includeSecrets:true): API_BASE=https://api.kapso.ai # KAPSO_API_BASE_URL - Network accessline 43
API_BASE=https://api.kapso.ai # KAPSO_API_BASE_URL - Access to secretsline 44
[Credential-related source omitted] - Network accessline 51
git clone --depth=1 https://github.com/gokapso/agent-skills /tmp/kapso-skills - Network accessline 130
[Credential-related source omitted] - Access to secretsline 130
[Credential-related source omitted] - Network accessline 132
# → { "url": "https://lookaside.fbsbx.com/...", "mime_type": "...", "file_size": ..., "id": "...", "sha256": "..." } - Network accessline 136
[Credential-related source omitted] - Access to secretsline 136
[Credential-related source omitted] - Network accessline 163
Use the Kapso platform endpoints via curl (no CLI needed): - Access to secretsline 167
[Credential-related source omitted] - Network accessline 169
[Credential-related source omitted] - Network accessline 170
[Credential-related source omitted] - Access to secretsline 170
[Credential-related source omitted] - Network accessline 173
[Credential-related source omitted] - Network accessline 174
[Credential-related source omitted] - Access to secretsline 174
[Credential-related source omitted] - Network accessline 177
[Credential-related source omitted] - Network accessline 178
[Credential-related source omitted] - Network accessline 179
[Credential-related source omitted] - Access to secretsline 179
[Credential-related source omitted] - Network accessline 182
[Credential-related source omitted] - Network accessline 183
[Credential-related source omitted] - Access to secretsline 183
[Credential-related source omitted] - Network accessline 199
[Credential-related source omitted] - Access to secretsline 199
[Credential-related source omitted] - Network accessline 236
[Credential-related source omitted] - Access to secretsline 236
[Credential-related source omitted] - Network accessline 286
[Credential-related source omitted] - Access to secretsline 286
[Credential-related source omitted] - Network accessline 302
[Credential-related source omitted] - Access to secretsline 302
[Credential-related source omitted] - Network accessline 320
[Credential-related source omitted] - Access to secretsline 320
[Credential-related source omitted] - Access to secretsline 342
[Credential-related source omitted]
templates/skills/serply-search/SKILL.md
- Network accessline 8
Serply (https://serply.io) is a Google SERP API. It returns the ranked organic results for a keyword query, and exposes Google News and Google Scholar as separate endpoints. API reference: https://serply.io/docs - Access to secretsline 27
[Credential-related source omitted] - Network accessline 30
The value comes back at `configs[0].value`. Export to env or pass inline. Keys come from https://serply.io - Network accessline 35
[Credential-related source omitted] - Access to secretsline 35
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Network accessline 54
"realPosition": 1, "result_type": "organic", "link": "https://bun.com/guides/ecosystem/drizzle" - Network accessline 55
"result_type": "organic", "link": "https://bun.com/guides/ecosystem/drizzle" } - Network accessline 56
"link": "https://bun.com/guides/ecosystem/drizzle" - Network accessline 69
[Credential-related source omitted] - Access to secretsline 69
[Credential-related source omitted] - Access to secretsline 70
[Credential-related source omitted] - Network accessline 76
[Credential-related source omitted] - Access to secretsline 76
[Credential-related source omitted] - Access to secretsline 77
[Credential-related source omitted]
templates/skills/serply-search/config.json
- Access to secretsline 10
[Credential-related source omitted]
templates/skills/serply-search/content.md
- Network accessline 3
Serply (https://serply.io) is a Google SERP API. It returns the ranked organic results for a keyword query, and exposes Google News and Google Scholar as separate endpoints. API reference: https://serply.io/docs - Access to secretsline 22
[Credential-related source omitted] - Network accessline 25
The value comes back at `configs[0].value`. Export to env or pass inline. Keys come from https://serply.io - Network accessline 30
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Access to secretsline 31
[Credential-related source omitted] - Network accessline 49
"realPosition": 1, "result_type": "organic", "link": "https://bun.com/guides/ecosystem/drizzle" - Network accessline 50
"result_type": "organic", "link": "https://bun.com/guides/ecosystem/drizzle" } - Network accessline 51
"link": "https://bun.com/guides/ecosystem/drizzle" - Network accessline 64
[Credential-related source omitted] - Access to secretsline 64
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Network accessline 71
[Credential-related source omitted] - Access to secretsline 71
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 500 facts
- Executable script in a comment of a file that runsclaude-mod/types/index.d.ts:1Low confidence
- Access to secrets in prose of the SKILL.mdinvestigate-sentry-issue/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdinvestigate-sentry-issue/SKILL.md:22Low confidence
- Network access in prose of the SKILL.mdinvestigate-sentry-issue/SKILL.md:32Low confidence
- Executable script in code of a file that runsscripts/check-pr-body.ts:1High confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:13Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:13Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:14Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:14Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:15Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:15Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:16Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:16Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:17Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:17Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueskills/agent-swarm/SKILL.md:17Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueagent-swarm/SKILL.md:17Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:18Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:18Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:19Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:19Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:20Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:20Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:21Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:21Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:22Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:22Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:23Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:23Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:24Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:24Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:25Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:25Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:26Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:26Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:27Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:27Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:28Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:28Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:32Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:32Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:33Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:33Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:34Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:34Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:35Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:35Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:36Low confidence
- Network access in prose of the SKILL.mdagent-swarm/SKILL.md:36Low confidence
- Network access in prose of the SKILL.mdskills/agent-swarm/SKILL.md:37Low confidence
and 450 more
Only the first 500 facts are listed.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugin/pi-skills/close-issue/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Native | Manifest gemini-extension.json | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugin/pi-skills/close-issue/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugin/pi-skills/close-issue/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/desplega-ai-agent-swarm/)