Not in the top 1,000 by GitHub stars
arronKler/herdr-skills
Coordinate coding agents in Herdr with assign, handoff, result collection, and follow-up messages. Install with npx skills.
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
skills/herdr-dispatch/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4b730ea7278b
No earlier version was observed for comparison.
skills/herdr-swarm/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4b730ea7278b
No earlier version was observed for comparison.
21GitHub stars
0stars in 7 days
2skills in this repository
0commits in 30 days
Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- herdr-dispatch
skills/herdr-dispatch - herdr-swarm
skills/herdr-swarm
How it works
herdr-dispatch
When your agent uses it
Dispatch peer coding agents through Herdr using assign, handoff, and send_message. Use when inside a Herdr pane and the user wants Claude, Codex, Pi, omp, Grok Build, Cursor, or another CLI worker spawned, tasked, collected, or followed up. Triggers include herd-dispatch, assign a worker, handoff to Codex, send_message to a pane, fan-out agents, peer review across CLIs, grok-build worker, cursor-agent model.
What it loads into context
Frontmatter
127 tokensAlways available to the agent
SKILL.md
3,375 tokensWhen the skill is activated
Reference documents
2,220 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preconditions
- Tools
- Assign (async)
- Handoff (sync)
- Send message
- Supervise the whole wave
- Surprise memory (field guide)
- Model
- Talking
- Routing defaults
- Status handling
- Cleanup
- Placement
- Efficiency
- References
Scripts executed separately
scripts/dispatch_store.pyscripts/herd-dispatchscripts/test_dispatch_runtime.pyscripts/test_herd_dispatch.py
Files
SKILL.mdcore14,163 bytesSKILL.mdcore14,163 bytesSKILL.mdcore14,163 bytesSKILL.mdcore14,163 bytesSKILL.mdcore14,163 bytesSKILL.mdcore14,163 bytesSKILL.mdcore14,163 bytesSKILL.mdcore14,163 bytesSKILL.mdcore14,163 bytesSKILL.mdcore14,163 bytesassets/brief-template.mddoc314 bytesreferences/envelope.mddoc2,435 bytesreferences/errors.mddoc3,757 bytesreferences/install.mddoc2,515 bytesscripts/dispatch_store.pyruns4,452 bytesscripts/herd-dispatchruns68,202 bytesscripts/test_dispatch_runtime.pyruns19,255 bytesscripts/test_herd_dispatch.pyruns29,118 bytes
Read SKILL.md
# Herdr Dispatch
Captain protocol for running other coding CLIs as workers inside Herdr. Call the bundled script. Do not improvise raw `herdr agent start` / `wait` / `prompt` sequences.
## Preconditions
1. Run `scripts/herd-dispatch doctor` first. It must report `"ok": true`, `"herdr": true`, and `self.pane_id`.
2. If doctor prints `"ok": false` for any reason (including `HERDR_ENV!=1`, missing verbs, or unresolved captain pane), stop. Show the JSON to the human. Do not debug by running raw `herdr agent` commands.
3. Never target the captain pane. The script refuses self-operations; do not bypass it.
4. Never run bare `herdr` (that attaches the TUI and hangs). Do not run bare `herdr agent` either; kinds come from doctor JSON or `herdr agent start --help`.
5. Workers must not dispatch further workers. Only the captain uses this skill.
## Tools
herdr-swarm
When your agent uses it
Run a small agent swarm (3-8 workers) through Herdr for large tasks that one agent cannot hold in context — goal decomposition into an ownership-split task tree, merge queue with neutral arbitration, shared decision log, field guide memory, hidden benchmarks. Use when the user wants a swarm, fan-out implementation of a big spec, multi-agent build from a spec, or says swarm/蜂群. Built strictly on top of the herdr-dispatch skill.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
1,689 tokensWhen the skill is activated
Reference documents
2,385 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preconditions
- Roles
- Scale limits
- Model mix
- Protocol
- Failure modes to prevent
- Benchmarking a swarm
- Hard rules
Files
SKILL.mdcore7,549 bytesSKILL.mdcore7,549 bytesreferences/benchmarking.mddoc1,396 bytesreferences/field-guide.mddoc1,738 bytesreferences/merge-queue.mddoc2,486 bytesreferences/review.mddoc1,520 bytesreferences/task-tree.mddoc2,333 bytestemplates/leaf-brief.mddoc1,325 bytes
Read SKILL.md
# Herdr Swarm
Small-scale swarm protocol, distilled from Cursor's "Agent swarms and the new model economics" (Jul 2026): scalability comes from **context efficiency and coordination discipline**, not raw parallelism. This skill is the orchestration layer; it never touches `herdr` directly — all spawning, collecting, and messaging goes through the **herdr-dispatch** skill's verbs (`doctor`, `assign`, `watch`, `collect`, `send`, `handoff`, `stop`).
## Preconditions
1. herdr-dispatch must be installed and its `doctor` must pass. If not, stop and tell the human.
2. The task must be big enough that one agent would lose context: multiple modules, a full spec, hours of work. For a single-file fix, use herdr-dispatch directly instead.
3. `--worktree` isolation is mandatory for every implementation leaf. Read-only leaves may share the main tree.
## Roles
- **Captain (this session) = planner.** Decomposes, decides, arbitrates merge order, reviews. The captain never implements code itself and never hand-waves a design decision into a brief — undecided design questions stop the tree until the captain decides them (or asks the human).
- **Workers = executors.** One leaf each. Workers do not plan, do not dispatch, and do not talk to each other. All cross-worker information flows through files the captain points at.Skills included
- herdr-dispatch
- herdr-swarm
Repository facts
- License
- MIT
- Created
- Sep 9, 2026
- Last pushed
- Sep 12, 2026
- Forks
- 1
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 10 notes
skills/herdr-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/herdr-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/herdr-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/herdr-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/herdr-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/herdr-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/herdr-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/herdr-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/herdr-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/herdr-swarm/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 1 network referencein 1 file: herdr-dispatch/references/install.md:7
- No hidden or obfuscated text
- No instruction overrides
- 4 executable scriptsin 4 files: herdr-dispatch/scripts/dispatch_store.py:1 herdr-dispatch/scripts/herd-dispatch:1 herdr-dispatch/scripts/test_dispatch_runtime.py:1 and 1 more
- 9 references to secretsin 2 files: herdr-dispatch/scripts/herd-dispatch:226 herdr-dispatch/scripts/test_dispatch_runtime.py:311
- No requests to vote in Hot
Show all 14 signals by file
skills/herdr-dispatch/references/install.md
- Network accessline 7
Use the [Vercel skills CLI](https://github.com/vercel-labs/skills) to install directly from GitHub:
skills/herdr-dispatch/scripts/dispatch_store.py
- Executable scriptline 1
Executable file
skills/herdr-dispatch/scripts/herd-dispatch
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 226
[Credential-related source omitted] - Access to secretsline 231
[Credential-related source omitted] - Access to secretsline 232
[Credential-related source omitted] - Access to secretsline 233
[Credential-related source omitted] - Access to secretsline 1897
[Credential-related source omitted] - Access to secretsline 1934
[Credential-related source omitted] - Access to secretsline 1969
[Credential-related source omitted]
skills/herdr-dispatch/scripts/test_dispatch_runtime.py
skills/herdr-dispatch/scripts/test_herd_dispatch.py
- Executable scriptline 1
#!/usr/bin/env python3
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.
Signal confidence: 14 facts
- Network access in prose of documentationherdr-dispatch/references/install.md:7Low confidence
- Executable script in prose of a file that runsherdr-dispatch/scripts/dispatch_store.py:1Low confidence
- Executable script in code of a file that runsherdr-dispatch/scripts/herd-dispatch:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueherdr-dispatch/scripts/herd-dispatch:226Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueherdr-dispatch/scripts/herd-dispatch:231Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueherdr-dispatch/scripts/herd-dispatch:232Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueherdr-dispatch/scripts/herd-dispatch:233Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueherdr-dispatch/scripts/herd-dispatch:1897Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueherdr-dispatch/scripts/herd-dispatch:1934Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueherdr-dispatch/scripts/herd-dispatch:1969Low confidence
- Executable script in prose of a testherdr-dispatch/scripts/test_dispatch_runtime.py:1Low confidence
- Access to secrets in code of a test: a variable, placeholder or call, not a stored valueherdr-dispatch/scripts/test_dispatch_runtime.py:311Low confidence
- Access to secrets in code of a test: a variable, placeholder or call, not a stored valueherdr-dispatch/scripts/test_dispatch_runtime.py:330Low confidence
- Executable script in code of a testherdr-dispatch/scripts/test_herd_dispatch.py:1Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/herdr-dispatch/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/herdr-dispatch/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/herdr-dispatch/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/herdr-dispatch/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/herdr-dispatch/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/herdr-dispatch/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.
