create-cmp
CLAUDE.md0 starsChanged 47 days agoMITView on GitHub
docs/NORTH-STAR.md governs. §12 is the document map, §10 the fit test every PR answers. The rules that are programs, and which program — ask these, not a document: - what this slice owes and when: node scripts/proof-plan.mjs (GATE-RULES Rule 4), enforced by .claude/settings.json → scripts/hooks/proof-gate.mjs. If it refuses you, it is right. - which lane this change is on, and what that lane therefore owes: node scripts/change-price.mjs (docs/CHANGE-FLOW-DESIGN.md §3). Advisory — it refuses nothing. - the lane returns both ways:…
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- template/AGENTS.mdAGENTS.md
- template/CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- npm-publishSkill
- plugin-refreshSkill
- cmp-auditSkill
- cmp-dev-clientSkill
- cmp-doctorSkill
- cmp-firebase-connectSkill
- cmp-inspectSkill
- cmp-newSkill
- cmp-previewSkill
- cmp-qa-prepSkill
- cmp-testSkill
- cmp-upgradeSkill
- grill-meSkill
The file
Files
create-cmp — the harness's own session map
docs/NORTH-STAR.md governs. §12 is the document map, §10 the fit test every PR answers.
The rules that are programs, and which program — ask these, not a document:
- what this slice owes and when:
node scripts/proof-plan.mjs(GATE-RULES Rule 4), enforced by.claude/settings.json→scripts/hooks/proof-gate.mjs. If it refuses you, it is right. - which lane this change is on, and what that lane therefore owes:
node scripts/change-price.mjs(docs/CHANGE-FLOW-DESIGN.md §3). Advisory — it refuses nothing. - the lane returns both ways:
node scripts/framework-check.mjs - a stage's exit:
node scripts/stage-gate.mjs - counts and versions:
node scripts/ground-truth.mjs, never by hand - a defect's number:
node scripts/kd-next.mjs, never the highest number this branch can see
Trunk-based: branch → PR → gh pr merge --rebase --delete-branch → pull; one piece in flight.
Docs move in the same commit as the change. Nothing here restates a rule — a rule stated twice
drifts in one, and a program at the moment of decision beats prose read at session start.
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.

