trellis
CLAUDE.md5 starsChanged 9 days agoMITView on GitHub
Claude Code specifics (everything above is harness-agnostic): - Hooks, slash commands, skills, and agents live in .claude/ - see SETUP.md for what's wired. - The /tdd, /bug-report, and /worktree commands are thin wrappers around docs/methodology/ - auto-follow them without being asked to invoke them by name. - The optional local knowledge base in brain/ injects context via a UserPromptSubmit hook once initialized (see brain/README.md). Kill switch: PROJECT_BRAIN_DISABLE=1.
In this repository48 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/project.mdcCursor rule
- bug-reportSkill
- build-verification-skillSkill
- daily-briefSkill
- grill-designSkill
- launch-checkSkill
- learnSkill
- pin-guardrailSkill
- prd-to-issuesSkill
- review-dependency-updatesSkill
- security-auditSkill
- setupSkill
- tddSkill
- trellis-surveySkill
- trellis-syncSkill
- worktreeSkill
- write-a-prdSkill
- build-verification-skillSkill
- daily-briefSkill
- grill-designSkill
- launch-checkSkill
- learnSkill
- pin-guardrailSkill
- prd-to-issuesSkill
- review-dependency-updatesSkill
- security-auditSkill
- setupSkill
- trellis-surveySkill
- trellis-syncSkill
- write-a-prdSkill
- bug-reportSkill
- build-verification-skillSkill
- daily-briefSkill
- grill-designSkill
- launch-checkSkill
- learnSkill
- pin-guardrailSkill
- prd-to-issuesSkill
- review-dependency-updatesSkill
- security-auditSkill
- setupSkill
- tddSkill
- trellis-surveySkill
- trellis-syncSkill
- worktreeSkill
- write-a-prdSkill
The file
Files
CLAUDE.md
@AGENTS.md
Claude Code specifics (everything above is harness-agnostic):
- Hooks, slash commands, skills, and agents live in
.claude/- see SETUP.md for what's wired. - The
/tdd,/bug-report, and/worktreecommands are thin wrappers arounddocs/methodology/- auto-follow them without being asked to invoke them by name. - The optional local knowledge base in
brain/injects context via a UserPromptSubmit hook once initialized (seebrain/README.md). Kill switch:PROJECT_BRAIN_DISABLE=1.
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.