Not in the top 1,000 by GitHub stars
SponsioLabs/Sponsio
Deterministic safety solutions for probabilistic AI agents
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
plugins/sponsio-claude-code/skills/configure/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
0165673875b8 → 0165673875b8
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0165673875b8
No earlier version was observed for comparison.
plugins/sponsio-openclaw/skills/configure/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
0165673875b8 → 0165673875b8
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0165673875b8
No earlier version was observed for comparison.
sponsio/skills/sponsio/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
0165673875b8 → 0165673875b8
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 0165673875b8
No earlier version was observed for comparison.
ts/packages/sdk/skills/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
0165673875b8 → 0165673875b8
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0165673875b8
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 0165673875b898a70167663924c3e3f7a9a96c98
git clone --filter=blob:none --no-checkout https://github.com/SponsioLabs/Sponsio.git .hotskills/sponsiolabs-sponsio && git -C .hotskills/sponsiolabs-sponsio checkout --detach 0165673875b898a70167663924c3e3f7a9a96c98
# Copy each selected skill directory from .hotskills/sponsiolabs-sponsio into .claude/skills/<skill-name>/454GitHub stars
0stars in 7 days
4skills in this repository
22commits in 30 days
Heat
1.6- 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
How it works
configure
When your agent uses it
Use after `/plugin install sponsio-claude-code` to wire the runtime end-to-end. The plugin install only registers hooks + skills; the contract library and per-environment overrides are configured here. Bootstraps the per-plugin contract library tree at ~/.sponsio/plugins/, installs bundled starter libraries for popular MCP servers (github, filesystem, playwright), generates fresh starter libraries for plugins / MCP servers that don't ship one (via `sponsio plugin scan`), tunes the shipped rules to the user's actual environment (workspace path, expected call volume, dev/CI/prod profile), and verifies with a smoke test. Use when the user says any of "configure sponsio-claude-code", "set up sponsio-claude-code", "first-time setup of sponsio", "wire up sponsio in this Claude Code session", "add Sponsio guardrails for my MCP tools", "tune the plugin for my environment", "the plugin is too strict / too loose", "calibrate sponsio rules", "scan this plugin", "generate sponsio rules for X", "create a contract library for my plugin", "I just installed Y plugin / MCP server, what should sponsio block", or asks how to make sponsio-claude-code actually block things.
What it loads into context
Frontmatter
267 tokensAlways available to the agent
SKILL.md
5,744 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 (check silently first)
- Routing rules from a policy document
- Step 1 — bootstrap the library root
- Step 2 — enumerate the user's MCP servers
- Step 3a — bundled MCP servers (use `sponsio plugin install`)
- Step 3b — unbundled plugins (use `sponsio plugin scan`)
- Step 4 — tune the shipped rules to the user's actual environment
- Step 5 — verify the deny path actually works
- Step 6 — tell the user to reload the plugin
- Common configuration adjustments
- Troubleshooting
- What you must not do
Files
../../.claude-plugin/plugin.jsonasset354 bytes../../hooks/hooks.jsonasset286 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytesSKILL.mdcore23,029 bytes
Read SKILL.md
# sponsio-claude-code — configure the host shield
You are walking the user through configuring the **sponsio-claude-code**
plugin so it actually wraps tool calls in this Claude Code session.
Without these steps, the plugin loads but every per-plugin library
is empty and every tool call passes through unguarded.
The flow has two halves: **setup** (steps 1–2, 4–6) covers the common
case where the user runs popular MCP servers we ship starters for;
**scan** (step 3) covers plugins / MCP servers without a bundled
starter and lives inline because most sessions touch both halves.
## Prerequisites (check silently first)
configure
When your agent uses it
Use after installing the sponsio-openclaw plugin to wire the runtime end-to-end. The plugin install only registers hooks + skills; the contract library and per-environment overrides are configured here. Bootstraps the per-plugin contract library tree at ~/.sponsio/plugins/, generates fresh starter libraries for OpenClaw plugins / MCP servers via `sponsio plugin scan` (with `--introspect` to auto-discover tool inventory; the agent then applies the prompt from `sponsio plugin prompt openclaw` to extract semantic contracts using its own LLM context — no separate API call), tunes the shipped rules to the user's actual environment, and verifies with a smoke test. Use when the user says any of "configure sponsio-openclaw", "set up sponsio-openclaw", "first-time setup of sponsio for OpenClaw", "wire up sponsio in this OpenClaw session", "add Sponsio guardrails for my OpenClaw plugins", "tune the plugin for my environment", "the plugin is too strict / too loose", "calibrate sponsio rules", "scan this OpenClaw plugin", "generate sponsio rules for my OpenClaw plugin", "I just installed Y plugin / MCP server in OpenClaw, what should sponsio block", or asks how to make sponsio-openclaw actually block things.
What it loads into context
Frontmatter
287 tokensAlways available to the agent
SKILL.md
4,161 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 (check silently first)
- Routing rules from a policy document
- Step 1 — bootstrap the library root
- Step 2 — enumerate the user's plugins / MCP servers
- Step 3 — generate per-plugin libraries via `sponsio plugin scan`
- Step 4 — tune the rules
- Step 5 — verify the deny path
- Step 6 — tell the user to reload the plugin
- Common configuration adjustments
- Troubleshooting
- What you must not do
Files
SKILL.mdcore16,267 bytesSKILL.mdcore16,267 bytesSKILL.mdcore16,267 bytesSKILL.mdcore16,267 bytesSKILL.mdcore16,267 bytesSKILL.mdcore16,267 bytesSKILL.mdcore16,267 bytesSKILL.mdcore16,267 bytesSKILL.mdcore16,267 bytesSKILL.mdcore16,267 bytesSKILL.mdcore16,267 bytesSKILL.mdcore16,267 bytes
Read SKILL.md
# sponsio-openclaw — configure the host plugin
You are walking the user through configuring the **sponsio-openclaw**
plugin so it actually wraps tool calls in this OpenClaw session.
Without these steps, the plugin loads but every per-plugin library
is empty and every tool call passes through unguarded.
The plugin sends `host: "openclaw"` in its hook payload so the
runtime fallback library is `_host_openclaw` (OpenClaw canonical
tool names — `exec` / `read` / `write` / `edit` / `apply_patch` /
`web_fetch` / `send_message` — with `path` / `command` / `url`
params), not the Claude-Code-shaped `_host`. Both libraries live
under the same `~/.sponsio/plugins/` tree.
sponsio
When your agent uses it
Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails or runtime safety to an LLM agent, generate or refine a sponsio.yaml, audit tool configurations for risks (data leaks, unguarded writes, missing confirmations), explain or review existing contracts, check what Sponsio would have blocked (`sponsio report`), move from observe to enforce mode, or debug why a contract is (or isn't) firing. Triggers on phrases like "set up sponsio", "add sponsio", "install sponsio", "add guardrails", "monitor my agent", "harden my agent", "audit my agent", "generate contracts", "explain my sponsio.yaml", "sponsio report", "flip to enforce", "false positive", "why is this rule firing".
What it loads into context
Frontmatter
206 tokensAlways available to the agent
SKILL.md
12,447 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 this skill
- Prerequisites (run silently before any workflow)
- Editing contract YAML — write rules by file
- W1 — Initial setup
- W2 — Audit & refine (from scratch, or deepen an existing yaml)
- W2b — Author plugin / MCP-server contracts
- W2c — Subagent privilege boundary
- W3 — Tune in observe
- W4 — Flip to enforce
- W5 — Troubleshoot
- W6 — Discover missing contracts from traces
- YAML schema (what contracts look like)
- Pattern reference
- Integration snippets (paste into your agent entry file after onboard)
- What this skill does NOT do
- Public API surface (for Sponsio maintainers — do not break)
Files
SKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytesSKILL.mdcore48,861 bytes
Read SKILL.md
# Sponsio — Agent Safety Lifecycle Companion
Sponsio is a Python/TypeScript runtime safety layer for LLM agents: it evaluates deterministic contracts against each tool call and can block (enforce) or just log (observe) violations. The engine is deterministic-only. This skill covers the full lifecycle — first-time setup, contract authoring/review, observe-mode tuning, and flipping to enforce — by orchestrating Sponsio's CLI and explaining its output in plain language.
This skill does NOT reimplement Sponsio's logic; it calls the CLI and interprets results.
## When to use this skill
Dispatch by what the user is trying to do. Pick ONE workflow and follow it; do not run multiple workflows in one turn.
| User is… | → Workflow |
|---|---|
| Setting up Sponsio for the first time in a project ("add sponsio", "install sponsio", "add guardrails") | **W1 — Initial setup** (just dispatch ``sponsio init``) |
| Handing you a codebase and asking "what could go wrong?" / wants a fresh contract file from scratch / has a policy doc to encode | **W2 — Audit & refine** |sponsio
When your agent uses it
Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails or runtime safety to an LLM agent, generate or refine a sponsio.yaml, audit tool configurations for risks (data leaks, unguarded writes, missing confirmations), explain or review existing contracts, check what Sponsio would have blocked (`sponsio report`), move from observe to enforce mode, or debug why a contract is (or isn't) firing. Triggers on phrases like "set up sponsio", "add sponsio", "install sponsio", "add guardrails", "monitor my agent", "harden my agent", "audit my agent", "generate contracts", "explain my sponsio.yaml", "sponsio report", "flip to enforce", "false positive", "why is this rule firing".
What it loads into context
Frontmatter
206 tokensAlways available to the agent
SKILL.md
5,452 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 this skill
- Prerequisites (run silently before any workflow)
- W1 — Initial setup
- W2 — Audit & refine (from scratch, or deepen an existing yaml)
- W3 — Tune in observe
- W4 — Flip to enforce
- W5 — Troubleshoot
- YAML schema (what contracts look like)
- Pattern reference
- Integration snippets (W1 fallback when `--apply` can't patch)
- What this skill does NOT do
- Public API surface (for Sponsio maintainers — do not break)
Files
SKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytesSKILL.mdcore21,208 bytes
Read SKILL.md
# Sponsio — Agent Safety Lifecycle Companion
Sponsio is a Python/TypeScript runtime safety layer for LLM agents: it evaluates deterministic contracts against each tool call and can block (enforce) or just log (observe) violations. The engine is deterministic-only. This skill covers the full lifecycle — first-time setup, contract authoring/review, observe-mode tuning, and flipping to enforce — by orchestrating Sponsio's CLI and explaining its output in plain language.
This skill does NOT reimplement Sponsio's logic; it calls the CLI and interprets results.
## When to use this skill
Dispatch by what the user is trying to do. Pick ONE workflow and follow it; do not run multiple workflows in one turn.
| User is… | → Workflow |
|---|---|
| Setting up Sponsio for the first time in a project ("add sponsio", "install sponsio", "add guardrails") | **W1 — Initial setup** |
| Handing you a codebase and asking "what could go wrong?" / wants a fresh contract file from scratch / has a policy doc to encode | **W2 — Audit & refine** |Skills included
- configure
- configure
- sponsio
- sponsio
Repository facts
- License
- Apache-2.0
- Created
- Apr 4, 2026
- Last pushed
- Nov 6, 2026
- Forks
- 27
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 82 notes
plugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-claude-code/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-openclaw/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-openclaw/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-openclaw/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sponsio-openclaw/skills/configure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 3 dangerous shell commandsin 3 files: configure/SKILL.md:470 configure/SKILL.md:332 sponsio/SKILL.md:319
- 7 network referencesin 3 files: plugins/sponsio-claude-code/.claude-plugin/plugin.json:6 sponsio/SKILL.md:834 skills/SKILL.md:327
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 5 references to secretsin 3 files: sponsio/SKILL.md:37 skills/SKILL.md:33 configure/SKILL.md:121
- No requests to vote in Hot
Show all 15 signals by file
plugins/sponsio-claude-code/.claude-plugin/plugin.json
plugins/sponsio-claude-code/skills/configure/SKILL.md
plugins/sponsio-openclaw/skills/configure/SKILL.md
- Dangerous shell operationline 332
echo '{"hook_event_name":"PreToolUse","tool_name":"exec","tool_input":{"command":"rm -rf /"},"host":"openclaw"}' \
sponsio/skills/sponsio/SKILL.md
- Access to secretsline 37
[Credential-related source omitted] - Dangerous shell operationline 319
rm <staging-path> # delete after success - Access to secretsline 701
[Credential-related source omitted] - Network accessline 834
runtime: mode: observe # "observe" | "enforce" dashboard: http://localhost:8000 # URL | true | false | null - Network accessline 836
dashboard: http://localhost:8000 # URL | true | false | null
ts/packages/sdk/skills/SKILL.md
- Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 236
[Credential-related source omitted] - Network accessline 327
runtime: mode: observe # "observe" | "enforce" dashboard: http://localhost:8000 # URL | true | false | null - Network accessline 329
dashboard: http://localhost:8000 # URL | true | false | null
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: 12 facts
- Access to secrets in prose of the SKILL.mdconfigure/SKILL.md:121Low confidence
- Dangerous shell operation in code of the SKILL.mdconfigure/SKILL.md:470High confidence
- Dangerous shell operation in code of the SKILL.mdconfigure/SKILL.md:332High confidence
- Access to secrets in prose of the SKILL.mdsponsio/SKILL.md:37Low confidence
- Dangerous shell operation in code of the SKILL.mdsponsio/SKILL.md:319High confidence
- Access to secrets in prose of the SKILL.mdsponsio/SKILL.md:701Low confidence
- Network access in code of the SKILL.mdsponsio/SKILL.md:834High confidence
- Network access in code of the SKILL.mdsponsio/SKILL.md:836High confidence
- Access to secrets in prose of the SKILL.mdskills/SKILL.md:33Low confidence
- Access to secrets in prose of the SKILL.mdskills/SKILL.md:236Low confidence
- Network access in code of the SKILL.mdskills/SKILL.md:327High confidence
- Network access in code of the SKILL.mdskills/SKILL.md:329High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest plugins/sponsio-claude-code/.claude-plugin/plugin.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md plugins/sponsio-claude-code/skills/configure/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugins/sponsio-claude-code/skills/configure/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugins/sponsio-claude-code/skills/configure/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugins/sponsio-claude-code/skills/configure/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/sponsio-claude-code/skills/configure/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.
