OpenLearning
CLAUDE.md1 starsChanged 8 months agoMITView on GitHub
Activate these rules when I ask you to review a plan, design, or architecture — or when I'm working interactively outside the pipeline. BEFORE YOU START: Ask if I want one of two options: 1/ BIG CHANGE: Work through this interactively, one section at a time (Architecture → Code Quality → Tests → Performance) with at most 4 top issues in each section. 2/ SMALL CHANGE: Work through interactively ONE question per review section FOR EACH STAGE OF REVIEW: output…
In this repository7 other files it gives its agents.
- api-syncSkill
- auto-fixSkill
- code-reviewSkill
- doc-syncSkill
- e2e-test-featureSkill
- e2e-test-generalSkill
- test-auditSkill
The file
We split this CLAUDE.MD into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Before proposing any new pattern, utility, or abstraction, search the existing codebase for prior art.
- Distinctive: line 16
When running /pipeline, /quality-gate, or /doc-sync commands:
- Distinctive: line 19
Stop and ask for human input ONLY at gate failures after 3 retries, or when the story-analyzer identifies open questions in Phase 0.
- Distinctive: line 31
Ask if I want one of two options: 1/ BIG CHANGE: Work through this interactively, one section at a time (Architecture → Code Quality → …
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 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 rules (always active)
Engineering preferences
- DRY is important—flag repetition aggressively.
- Well-tested code is non-negotiable.
- "Engineered enough" — not under-engineered, not over-engineered.
- Handle more edge cases, not fewer; thoughtfulness > speed.
- Bias toward explicit over clever.
- Flag over-engineering: if a proposed abstraction only serves the current use case with no evidence of future reuse, call it out.
- Before proposing any new pattern, utility, or abstraction, search the existing codebase for prior art. If something similar exists, explain why reuse doesn't work before creating new.
Pipeline workflow
When running /pipeline, /quality-gate, or /doc-sync commands:
- Execute phases autonomously. Do NOT pause for interactive input between phases.
- Stop and ask for human input ONLY at gate failures after 3 retries, or when the story-analyzer identifies open questions in Phase 0.
- Plan mode rules below do NOT apply during pipeline execution.
Plan mode rules (only when reviewing plans, NOT during /pipeline)
Activate these rules when I ask you to review a plan, design, or architecture — or when I'm working interactively outside the pipeline.
BEFORE YOU START: Ask if I want one of two options: 1/ BIG CHANGE: Work through this interactively, one section at a time (Architecture → Code Quality → Tests → Performance) with at most 4 top issues in each section. 2/ SMALL CHANGE: Work through interactively ONE question per review section FOR EACH STAGE OF REVIEW: output the explanation and pros and cons of each stage's questions AND your opinionated recommendation and why, and then use AskUserQuestion. Also NUMBER issues and then give LETTERS for options and when using AskUserQuestion make sure each option clearly labels the issue NUMBER and option LETTER so the user doesn't get confused. Make the recommended option always the 1st option.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

