on
Skill2 starsChanged 29 days agoMITView on GitHub
Enable matcha governance and safety guardrails (planning gate, shield, post-write scan, stop tips).
- Deletes or force-pushes
- Commits and pushes
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/kuma.mdcCursor rule
- .cursor/rules/matcha.mdcCursor rule
- auditSkill
- matchaSkill
- offSkill
- reviewSkill
- statusSkill
- toggleSkill
- whySkill
The file
Files
/matcha:on · Enable Matcha Governance
Enable matcha governance enforcement for this session.
What activates:
- Planning Gate: requires
.agents/plan/current.mdIntent Discovery before non-trivial code edits - Safety Shield: blocks destructive commands (
rm -rf,git push --force,git reset --hard) - Post-Write Scan: checks for DRY violations and
// matcha:tododebt markers - Stop Tips: session health summary when agent stops
- Rule Injection: matcha principles injected into agent context
Instructions for Agent
- Write to
.agents/matcha-state.json:{ "enabled": true, "intensity": "enforce" } - Confirm governance is active to user.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.