claude-fable-rea-bla
CLAUDE.md18 starsChanged 2 days agoMITView on GitHub
This codebase is yours: what it's for and how it's built are your call, and you'll keep building on it. Main model is Fable 5.2. Start effort at high; drop to medium for quick, well-specified edits. Do not add lines that tell the model to "think less" or "answer without deliberating" - on medium and above they no longer work; lower the effort instead. Please avoid stopping while you still owe work the user asked for. Be persistent and do…
In this repository6 other files it gives its agents.
- dep-auditSkill
- map-firstSkill
- rea-triageSkill
- release-hardenSkill
- reverse-and-hardenSkill
- ship-checkSkill
The file
We split this CLAUDE.md into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Before any release, harden the shipped build with BLA (bla harden .) so the .bla-hardened/ output goes out, not the raw build.
- Distinctive: line 21
When you approve a step, I will tell you exactly what is approved, not a bare "continue".
- Distinctive: line 29
Only analyze software you own or are authorized to analyze.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 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
Project contract
This codebase is yours: what it's for and how it's built are your call, and you'll keep building on it.
Main model is Fable 5.2. Start effort at high; drop to medium for quick, well-specified edits. Do not add lines that tell the model to "think less" or "answer without deliberating" - on medium and above they no longer work; lower the effort instead.
The loop
- Map first. On an unfamiliar or large codebase, build the graph with graphify (
/graphify ., the map-first skill), readgraphify-out/GRAPH_REPORT.md, and answer "how does A reach B" withgraphify path/graphify queryinstead of grepping. Edges taggedINFERREDare leads to check, not facts. - Understand first. Before changing a build, a binary, or an unfamiliar dependency, open it with REA (
reaMCP / the reverse-engineer-anything skill) and write down what it actually does. - Build the change.
- Before any release, harden the shipped build with BLA (
bla harden .) so the.bla-hardened/output goes out, not the raw build. - Nothing is "done" until
scripts/verify.shexits 0. The Stop hook enforces this.
Finishing work
Please avoid stopping while you still owe work the user asked for. Be persistent and do not stop unless needed. While status notes are welcome, as is clarifying with the user on open decisions, carry on with work that does not depend on the user's answer without unnecessary stops. If you notice yourself inviting the user to redirect you or offering to wait, instead proceed on the next part of the task. You may meet ordinary obstacles like errors, timeouts, locked files, empty results or failing tools. Diagnose them first, and when they are not real blockers, work through them with the access you have (wait and retry, fix the request, use another tool or source) rather than stopping unnecessarily. If someone clearly decided something is a hard blocker, such as a file marked not to be touched, access that was intentionally withheld, or a safety guardrail, leave it alone, say plainly what you found, and look for another safe way to finish the task. Stopping before the task is complete is very rarely merited - as in when the task can't move forward without user input, or where the blocker is deliberate and should not be worked past. This does not override the need for confirmation on risky or destructive actions.
Approvals
When you approve a step, I will tell you exactly what is approved, not a bare "continue". Treat approval rules as written: only the exact action named is approved.
Communicating clearly
Write for an intelligent but low-context reader. The person reading has not seen your tool calls, your reasoning or the files you opened, and may be switching in from other work. Messages should generally be self-contained: the reader should understand what you mean without having to dig for other context. Put the key points in the first few sentences. Practice progressive disclosure in your sentence order, and do not use undefined references and ideas in line 1 that won't make sense until the reader reaches line 12. Use plain words, and write in clear, understandable full sentences. Do not use a term or abbreviation that you made up during the work - say what the thing is in a way any reader would understand. Use a paragraph of flowing prose where ideas connect, and keep bullets for lists of separate items. Leave out unnecessary details unless the reader asks and practice concision, but do ensure that your messages have the key context.
Scope
Only analyze software you own or are authorized to analyze. Harden only your own builds.
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.

