craft
AGENTS.md4 starsChanged 12 days agoMITView on GitHub
Commands/skills/agents use YAML frontmatter; keep counts, public interfaces, README, examples, breaking-change notices, and documentation synchronized. Python: explicit types, specific exceptions, pathlib, public API docstrings; validate paths and inputs, mock external dependencies, clean test artifacts. Coverage target: 90%+, including critical paths and edge/error cases. Required gates: python3 -m pytest tests/ -v, bash tests/test_dependency_management.sh, ./scripts/validate-counts.sh, configured Markdown lint, documentation build and link checks. Read the reference's Build/Lint/Test Commands and CI/CD Integration before committing or releasing. The exact pre-condensation instructions are preserved in…
In this repository42 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- system-architectSkill
- project-detectorSkill
- audit-routerSkill
- command-skill-token-efficiencySkill
- plugin-auditSkill
- sync-featuresSkill
- backend-designerSkill
- devops-helperSkill
- frontend-designerSkill
- git-workflowSkill
- dist-extrasSkill
- distribution-strategistSkill
- homebrew-formula-expertSkill
- homebrew-multi-formulaSkill
- homebrew-setup-wizardSkill
- homebrew-workflow-expertSkill
- architecture-decision-recordsSkill
- changelog-automationSkill
- claude-md-lifecycleSkill
- guard-auditSkill
- hooksSkill
- insights-applySkill
- mode-controllerSkill
- drive-engineSkill
- plan-orchestratorSkill
- repo-triageSkill
- session-stateSkill
- task-analyzerSkill
- workflow-engineSkill
- orchestrator-resilienceSkill
- project-plannerSkill
- preflight-checkSkill
- releaseSkill
- test-generatorSkill
- test-strategistSkill
- adhd-workflowSkill
- brainstorm-insightsSkill
- brainstormSkill
- grillSkill
- prompt-refinerSkill
- background-task-managerSkill
The file
Files
AGENTS.md - Development Guidelines for Craft Plugin
Working contract
Commands/skills/agents use YAML frontmatter; keep counts, public interfaces, README, examples, breaking-change notices, and documentation synchronized. Python: explicit types, specific exceptions, pathlib, public API docstrings; validate paths and inputs, mock external dependencies, clean test artifacts. Coverage target: 90%+, including critical paths and edge/error cases.
Required gates: python3 -m pytest tests/ -v, bash tests/test_dependency_management.sh, ./scripts/validate-counts.sh, configured Markdown lint, documentation build and link checks. Read the reference's Build/Lint/Test Commands and CI/CD Integration before committing or releasing.
On-demand requirements
The exact pre-condensation instructions are preserved in /Users/davood/.codex/reference/repos/dev-tools-craft/AGENTS-detail-2026-10-12.md. Before a task, read only its applicable sections: scientific/model changes, builds/tests, source conventions, dependency/API changes, packaging/releases, configuration/imports, deployment, or workflow cleanup. Every applicable requirement and verification gate there remains binding; this shorter file does not waive any. Do not load the whole reference for unrelated tasks. Historical versions, counts, results and completed-work snapshots are not live status: check the owning source and .STATUS. Current user instructions and project holds take precedence.
Preserve unrelated changes and concurrent sessions. Required checks must pass before claiming completion; inspect actual rendered artifacts where applicable. Author review/submission holds remain active until explicitly lifted. Passing checks never authorizes submission, merge, release, deployment, email sending or privacy changes.
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.

