ai-usage-app
CLAUDE.md0 starsChanged 31 days agoMITView on GitHub
- Skills: the repository skills listed in AGENTS.md live in .agents/skills/<name>/SKILL.md. Reading the matching file before work in its area is mandatory. Thin wrappers in .claude/skills/ make the same skills invocable by name; the canonical text stays in .agents/skills/. - Agents: aiu-reviewer and aiu-implementer in .claude/agents/ load the contracts in .agents/agents/; so do aiu-scout and aiu-runner, the lean helpers (CONTRIBUTING, Helper agents), which start without the CLAUDE.md files. When they are not loaded (for example, added during the session), use…
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- convergence-reviewSkill
- ecoSkill
- plan-executionSkill
- planning-and-variantsSkill
- post-deploy-checkSkill
- provider-evidenceSkill
- receiving-code-reviewSkill
- security-lifecycleSkill
- systematic-debuggingSkill
- verification-before-completionSkill
- convergence-reviewSkill
- ecoSkill
- plan-executionSkill
- planning-and-variantsSkill
- post-deploy-checkSkill
- provider-evidenceSkill
- receiving-code-reviewSkill
- security-lifecycleSkill
- systematic-debuggingSkill
- verification-before-completionSkill
The file
Files
@AGENTS.md
Claude Code
- Skills: the repository skills listed in AGENTS.md live in
.agents/skills/<name>/SKILL.md. Reading the matching file before work in its area is mandatory. Thin wrappers in.claude/skills/make the same skills invocable by name; the canonical text stays in.agents/skills/. - Agents:
aiu-reviewerandaiu-implementerin.claude/agents/load the contracts in.agents/agents/; so doaiu-scoutandaiu-runner, the lean helpers (CONTRIBUTING, Helper agents), which start without the CLAUDE.md files. When they are not loaded (for example, added during the session), use a general-purpose agent and tell it to read and follow the contract file. - Subagent models: pass the
modelandeffortof the role's entry in.agents/models/(normal.yaml, oreco.yamlwhile economy mode is on) on every Agent call; the wrappers in.claude/agents/set no model or effort (CONTRIBUTING, Subagent models). - Project settings in
.claude/settings.jsonhold deny rules and plugin switches only (CONTRIBUTING, Agent permissions).
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.