cadence
CLAUDE.md1 starsChanged 3 months agoMITView on GitHub
Skill and agent text in this repo must route every Cadence config read through scripts/resolve-config.js (invoked as node "${CLAUDE_PLUGIN_ROOT}/scripts/resolve-config.js"). Never write skill or agent text that instructs a direct read of .cadence/config.yaml, .cadence/config.local.yaml, or defaults/config.default.yaml — prose resolution is exactly the failure the resolver exists to remove. The contract (output shape, exit codes, hard-stop rule, sanctioned write paths) lives in skills/_shared/config-resolution.md. node --test 'scripts/*.test.js' runs the Node script suites (migrate-config.test.js, resolve-config.test.js, notion-rest.test.js, notion-write.test.js, notion-read.test.js, and skill-structure.test.js, which checks the shipped…
In this repository11 other files it gives its agents.
- docs-siteSkill
- c-auditSkill
- c-brainstormSkill
- c-checkSkill
- c-designSkill
- c-executeSkill
- c-explainSkill
- c-find-bugsSkill
- c-planSkill
- c-validateSkill
- c-worktreeSkill
The file
Files
Cadence repo conventions
Config reads go through the resolver
Skill and agent text in this repo must route every Cadence config read through scripts/resolve-config.js (invoked as node "${CLAUDE_PLUGIN_ROOT}/scripts/resolve-config.js"). Never write skill or agent text that instructs a direct read of .cadence/config.yaml, .cadence/config.local.yaml, or defaults/config.default.yaml — prose resolution is exactly the failure the resolver exists to remove. The contract (output shape, exit codes, hard-stop rule, sanctioned write paths) lives in skills/_shared/config-resolution.md.
Tests
node --test 'scripts/*.test.js' runs the Node script suites (migrate-config.test.js, resolve-config.test.js, notion-rest.test.js, notion-write.test.js, notion-read.test.js, and skill-structure.test.js, which checks the shipped skill and agent text), and bash scripts/test-merge-lock.sh smoke-tests merge-lock.sh. Run both before any PR that touches scripts/, skills/, agents/, or templates/.
Skill descriptions
A skill's description: frontmatter says only when to use the skill: it starts with "Use when", stays under 250 characters, and never summarizes the workflow. An agent that reads a workflow summary in the description can follow it instead of the skill body. Guarantees ("never writes code") belong in the body. scripts/skill-structure.test.js enforces the shape.
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.