codex-howto
AGENTS.md15 starsChanged 3 months agoMITView on GitHub
Maintain an accurate, engineering-first learning guide for OpenAI Codex. - Keep product behavior aligned with official OpenAI documentation. - Label community practices and opinions clearly. - Do not add credentials, destructive examples, or full-access defaults. - Keep modules progressive: outcome, concepts, exercise, verification, sources. - Keep skill bodies concise; put optional detail in direct references/. - Preserve attribution to luongnv89/claude-howto as inspiration. - For work that depends on prior decisions, experiments, or established Codex guidance, read knowledge/index.md first and load…
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 31,774 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 repository10 other files it gives its agents.
- examples/AGENTS.mdAGENTS.md
- build-backendSkill
- build-frontendSkill
- engineering-loopSkill
- maintain-codex-wikiSkill
- operate-devopsSkill
- orchestrate-engineeringSkill
- review-codeSkill
- review-securitySkill
- test-softwareSkill
The file
We split this AGENTS.md into the rules it gives an agent
7 rules. About 1 is common, 5 are distinctive, and 1 is very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈5
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
- could be automatic: a setting could enforce it
- Distinctive: line 9
Keep product behavior aligned with official OpenAI documentation.
- Common: line 11
Do not add credentials, destructive examples, or full-access defaults.
- Distinctive: line 12
Keep modules progressive: outcome, concepts, exercise, verification, sources.
- Very specific: line 13
Keep skill bodies concise.
- Distinctive: line 17
Treat wiki queries as read-only unless the user explicitly requests capture, ingest, archive, or promotion.
- Distinctive: line 42
All relative Markdown links resolve.
- Distinctive: line 43
Every skill has valid frontmatter and UI metadata.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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
Repository guidance
Purpose
Maintain an accurate, engineering-first learning guide for OpenAI Codex.
Editing rules
- Keep product behavior aligned with official OpenAI documentation.
- Label community practices and opinions clearly.
- Do not add credentials, destructive examples, or full-access defaults.
- Keep modules progressive: outcome, concepts, exercise, verification, sources.
- Keep skill bodies concise; put optional detail in direct
references/. - Preserve attribution to
luongnv89/claude-howtoas inspiration. - For work that depends on prior decisions, experiments, or established Codex
guidance, read
knowledge/index.mdfirst and load only relevant pages. - Treat wiki queries as read-only unless the user explicitly requests capture, ingest, archive, or promotion.
Pull requests
This personal open-source repository does not require Jira tickets. Use a descriptive branch and PR title; link relevant GitHub issues when applicable.
Validation
Run:
python3 scripts/validate_repo.py
python3 skills/maintain-codex-wiki/scripts/wiki_lint.py .For each changed skill, also run:
python3 /path/to/skill-creator/scripts/quick_validate.py skills/<skill-name>Definition of done
- All relative Markdown links resolve.
- Every skill has valid frontmatter and UI metadata.
- Living-wiki pages have registered sources and pass deterministic lint.
- Examples are safe and contain no placeholder secrets.
- Version-sensitive claims include an official source or verification note.
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.