clean-code-skill
AGENTS.md1 starsChanged 5 days agoMITView on GitHub
Guidance for AI coding agents (and humans) working on this repository. For the contribution workflow see CONTRIBUTING.md. The clean-code Agent Skill (skills/clean-code/), its Claude Code plugin manifests (.claude-plugin/), generated rule-file adapters (adapters/), and the tooling that validates and installs them (scripts/, tests/). - Never reproduce the book. No verbatim text, code, examples, figures, or chapter structure from Clean Code. Original wording, organized by topic. Rule codes and framework names are fine. - Keep the disclaimer in skills/clean-code/SKILL.md, README.md, and NOTICE.md…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 32,671 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repositoryOne other file it gives its agents.
- clean-codeSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 14
Never reproduce the book: No verbatim text, code, examples, figures, or chapter structure from *Clean Code*.
- Very specific: line 38
Run all four before finishing a change.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.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
AGENTS.md
Guidance for AI coding agents (and humans) working on this repository. For the contribution workflow see CONTRIBUTING.md.
What this repo is
The clean-code Agent Skill (skills/clean-code/), its Claude Code plugin manifests
(.claude-plugin/), generated rule-file adapters (adapters/), and the tooling that validates
and installs them (scripts/, tests/).
Hard rules
- Never reproduce the book. No verbatim text, code, examples, figures, or chapter structure from Clean Code. Original wording, organized by topic. Rule codes and framework names are fine.
- Keep the disclaimer in
skills/clean-code/SKILL.md,README.md, andNOTICE.mdaccurate. - Frontmatter portability.
SKILL.mdfrontmatter may use onlyname,description,license,compatibility,metadata,allowed-tools. Thenamemust equal the directory name (clean-code). Keep thedescriptionunder 1024 characters and rich in trigger words. - Every file in
skills/clean-code/references/must be linked fromSKILL.md. Links are relative.SKILL.mdstays under 500 lines. - Do not hand-edit generated files. Edit
adapters/digest.md, then runpython3 scripts/build_adapters.py. - Keep versions in sync:
.claude-plugin/plugin.json,.claude-plugin/marketplace.json,metadata.versioninSKILL.md, and the top entry inCHANGELOG.md. - Catalog completeness.
references/catalog.mdmust keep a row for every code in C1-C5, E1-E2, F1-F4, G1-G36, N1-N7, and T1-T9.
Commands
python3 scripts/validate.py
python3 -m unittest discover -s tests
bash tests/test_install.sh
shellcheck scripts/*.sh tests/*.shRun all four before finishing a change. Update CHANGELOG.md under Unreleased.
Style
- Markdown: ATX headings, one sentence per idea, tables for catalogs, fenced code with a language.
- Shell: Bash with
set -euo pipefail, quoted expansions, ShellCheck clean. - Python: standard library only, type hints, Python 3.9+.
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.

