codify
Skill2 starsChanged 14 days agoMITView on GitHub
Turn a standard the user sets, a correction they make or an instruction they repeat into the strongest durable enforcement - a test or CI check, a lint rule, a git hook, a Claude Code hook, a skill or agent instruction, an AGENTS.md rule, or (last) a memory - and retrofit what already violates it. Use whenever the user corrects how something is done, says "always" or "never", or repeats an instruction.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- vic-lsh/agent-skillstheir own version, first seen Nov 8, 2026
- hollandkevint/thinkhaven-method-kittheir own version, first seen Oct 20, 2026
- DoKu67/claude-code-skilstheir own version, first seen Oct 16, 2026
- yuanhaorannnnnn/agent-skillstheir own version, first seen Sep 18, 2026
- treekey/claude-codifytheir own version, first seen Jul 6, 2026
- anombyte93/atlas-ai-skillstheir own version, first seen Apr 26, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- anombyte93/codify★ 4same name
- DoKu67/claude-code-skils★ 4same name
- vic-lsh/agent-skills★ 2same name
- treekey/claude-codify★ 1same name
- anombyte93/atlas-ai-skills★ 0same name
- hollandkevint/thinkhaven-method-kit★ 0same name
- yuanhaorannnnnn/agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/CLAUDE.mdCLAUDE.md
- starter/CLAUDE.mdCLAUDE.md
- template/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- add-moduleSkill
- add-operationSkill
- raise-the-barSkill
- releaseSkill
- reviewSkill
- scaffold-pluginSkill
- self-auditSkill
- ship-smallSkill
- write-adrSkill
- write-testsSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
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 23
Prefer one strong check over several weak reminders.
- Distinctive: line 32
Commit with a conventional message whose body says what was codified and at which level.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Codify
An intervention the user has to make twice is a missing check. Make it durable at the strongest level that can express it, prove that level catches a violation, and fix the existing violations.
Choose the level (strongest first)
| Level | Use when | Where |
| Test or CI check | The rule is checkable from files: structure, presence, naming, links, frontmatter, AST patterns | tests/unit/*_test.py (AST and file checks like standards_test.py), CI job |
| Lint or type rule | An existing tool has a rule for it | pyproject.toml (ruff, mypy, pyright, import-linter), typos.toml, zizmor |
| Git hook | It must hold for every tool and person before code is shared | .pre-commit-config.yaml (prek) |
| Claude Code hook | It is about how an agent works (commands, edits, finishing) | .claude/hooks/, .claude/settings.json |
| Skill or agent | It is a procedure or a judgment call | .claude/skills/, .claude/agents/ |
| AGENTS.md / CLAUDE.md | It is a working agreement no tool can check | one line, where the topic already lives |
| Memory | It is about the user personally, not the repository | Claude Code memory |
Prefer one strong check over several weak reminders; don't also write a prose rule for what a test enforces.
Steps
- State the standard in one sentence, as the user meant it. If it is ambiguous, ask once.
- Pick the level from the table and implement it. Plugins inherit the template: put shared checks where
scripts/sync_template.pyor the template symlinks carry them. - Show it works: introduce a violation, watch the check fail, remove it.
- Fix the existing violations in the same change.
- Commit with a conventional message whose body says what was codified and at which level.
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.