atelier
CLAUDE.md2 starsChanged 5 months agoMITView on GitHub
This project's full AI contract lives in AGENTS.md — read it in full. It is canonical; this file only adds Claude Code specifics. 1. Read PROJECT.md. 2. If its status is UNINITIALIZED, run the start skill (the onboarding interview) before anything else. 3. Otherwise, note the active mode and current phase and proceed within the mode's rules. Invoke with /<name>; each skill just runs the matching playbook in docs/playbooks/, so behavior stays consistent across tools. If you keep cross-session memory,…
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/methodology.mdcCursor rule
- adr-reviewSkill
- lessonSkill
- milestoneSkill
- modeSkill
- progressSkill
- startSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
If its status is UNINITIALIZED, run the start skill (the onboarding interview) before anything else.
- Very specific: line 30
If you keep cross-session memory, record: the user's background and goals (from onboarding), the active mode, and where the current phase …
≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CLAUDE.md
This project's full AI contract lives in AGENTS.md — read it
in full. It is canonical; this file only adds Claude Code specifics.
@AGENTS.md
First thing, every session
- Read
PROJECT.md. - If its status is
UNINITIALIZED, run thestartskill (the onboarding interview) before anything else. - Otherwise, note the active mode and current phase and proceed within the mode's rules.
Skills available in this repo
Invoke with /<name>; each skill just runs the matching playbook in
docs/playbooks/, so behavior stays consistent across tools.
/start— onboarding interview: turn this template into your project./mode— switch betweenguided,collab, andautopilot./milestone— produce the next guided milestone build doc./progress— compare repo state to the roadmap, log progress, plan next session./adr-review— review an ADR you've written (never write one for you)./lesson— produce or continue a deep-dive learning-track lesson.
Memory
If you keep cross-session memory, record: the user's background and goals (from
onboarding), the active mode, and where the current phase stands. Re-read
PROJECT.md each session rather than trusting stale memory — it is the live
state.
Mode reminder
The mode in PROJECT.md is binding. In guided mode you must never create
or edit application code — deliver it as an annotated snippet for the user to
type. See AGENTS.md §2.
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.

