Ghost / templates
CLAUDE.md3 starsChanged 7 months agoMITView on GitHub
This file is read at the start of every session. Keep it lean. Remove stale entries. Target: under 80 lines. Anything longer belongs in docs/. Name: [project name] Purpose: [one sentence — what this does and why] Status: [active / maintenance / MVP / in-progress] Last updated: [date] by Claude after [task name]
- Reads credentials
In this repositoryOne other file it gives its agents.
- context-optimizerSkill
The file
Files
CLAUDE.md — Project Memory
This file is read at the start of every session. Keep it lean. Remove stale entries. Target: under 80 lines. Anything longer belongs in docs/.
Project
Name: [project name] Purpose: [one sentence — what this does and why] Status: [active / maintenance / MVP / in-progress]
Stack
| Layer | Tech |
| Frontend | [e.g. React + TypeScript + Vite] |
| Backend | [e.g. Node.js + Express] |
| Database | [e.g. Supabase / PostgreSQL] |
| Hosting | [e.g. Vercel] |
| Auth | [e.g. Supabase Auth / JWT] |
Commands
# Dev
npm run dev
# Build
npm run build
# Test
npm run test
# Lint
npm run lint
# Deploy
[deploy command]Architecture Rules
- [e.g. All API calls go through /lib/api.ts — never call fetch directly in components]
- [e.g. State managed via Zustand — no prop drilling beyond 2 levels]
- [e.g. Auth guard wraps all protected routes in /components/AuthGuard.tsx]
Naming & Style
- [e.g. Files: kebab-case. Components: PascalCase. Functions: camelCase.]
- [e.g. CSS: Tailwind utility classes only, no custom CSS unless absolutely necessary]
- [e.g. Commits: conventional commits — feat/fix/chore/docs]
Do Not Repeat (read before every task)
- Never store secrets in code — use .env + Supabase vault
- Always validate inputs server-side, not just client-side
- Run lint before every commit
- [Add project-specific rules here]
Key Files
| File | Purpose |
src/lib/api.ts | Central API layer |
src/store/ | Global state |
src/components/AuthGuard.tsx | Auth protection |
| [add key files] | [purpose] |
Last updated: [date] by Claude after [task name]
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.