agentic-developer-handbook
CLAUDE.md34 starsChanged 42 days agoApache-2.0View on GitHub
Project principles live in .cursor/rules/project-principles.mdc, CONTRIBUTING.md, and docs/adr/. Follow them. Neither needs an API key or network model calls. The canonical Java version is 27 (ADR 0005); do not use preview or incubator features.
In this repository2 other files it gives its agents.
- .cursor/rules/project-principles.mdcCursor rule
- implement-loopSkill
The file
We split this CLAUDE.md into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Commit with the repository owner's configured Git identity only.
- Distinctive: line 8
Never add Claude, Anthropic, Cursor, or any other AI tool as a commit author or co-author.
- Very specific: line 9
Never add AI Co-Authored-By trailers to commit messages, and no "Generated with" AI attribution lines in commits or pull request …
- Very specific: line 10
Never change git config user.name or user.email automatically.
≈ “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
Claude Code instructions
Project principles live in .cursor/rules/project-principles.mdc, CONTRIBUTING.md, and docs/adr/. Follow them.
Commit authorship
- Commit with the repository owner's configured Git identity only.
- Never add Claude, Anthropic, Cursor, or any other AI tool as a commit author or co-author.
- Never add AI
Co-Authored-Bytrailers to commit messages, and no "Generated with" AI attribution lines in commits or pull request descriptions. - Never change
git config user.nameoruser.emailautomatically.
Validate before a pull request
./mvnw verify
python -m unittest discover -s scripts/tests -vNeither needs an API key or network model calls. The canonical Java version is 27 (ADR 0005); do not use preview or incubator features.
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.

