matcha / rules
Cursor rule2 starsChanged 29 days agoMITView on GitHub
Kuma MCP — safety and context runtime for AI agents
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,183 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
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/matcha.mdcCursor rule
- auditSkill
- matchaSkill
- offSkill
- onSkill
- reviewSkill
- statusSkill
- toggleSkill
- whySkill
The file
We split this kuma.mdc into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
MUST call kuma_context({ action: "init" }) at session start.
- Distinctive: line 12
MUST record gotchas IMMEDIATELY when a bug/quirk is found.
- Very specific: line 13
MUST call kuma_safety({ action: "verify" }) after edits.
- Distinctive: line 14
MUST NOT call actions outside the 13 core actions.
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
---
description: Kuma MCP — safety and context runtime for AI agents
alwaysApply: true
---
Kuma MCP tools: kuma_context, kuma_memory, kuma_safety.
Record what matters, skip what doesn't.
<kuma_obedience>
## 🔒 Obedience (non-negotiable)
- MUST call `kuma_context({ action: "init" })` at session start.
- MUST record gotchas IMMEDIATELY when a bug/quirk is found.
- MUST call `kuma_safety({ action: "verify" })` after edits.
- MUST NOT call actions outside the 13 core actions.
</kuma_obedience>
<kuma_workflow>
🧠 **Before coding:** `kuma_context({ action: "init" })`
🔬 **Unfamiliar code:** `kuma_context({ action: "research", scope: "<area>" })`
🐛 **Found a bug/quirk:** `kuma_memory({ action: "gotcha" })` (IMMEDIATELY)
🧭 **Chose between options:** `kuma_memory({ action: "decision" })`
🔀 **Traced a flow:** `kuma_memory({ action: "arch_flow" })` (max 5 files)
🛡️ **Before risky work / after edits:** `kuma_safety({ action: "guard" | "verify" })`
</kuma_workflow>
📖 Full rules: `.kuma/init.md`
📖 **Usage:**
• `kuma_context({ action: "init" })` — load project context (call first)
• `kuma_safety({ action: "guard" })` — safety check before risky ops
• `kuma_safety({ action: "verify", scope: "<area>" })` — verify after edits
• `.kuma/init.md` — full behavioral rules
• `.kuma/KNOWN_GOTCHAS.md` — gotchas · `.kuma/memories/decisions.md` — decisions (readable)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.