agent-docs SKILL.md skillA

agent-docs from dayfinggg/openai-codex-agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add dayfinggg/openai-codex-agent-skills/agent-docs@git:20261117.080857b

Pins git:20261117.080857b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
dayfinggg/openai-codex-agent-skills
Path
codex/skills/agent-docs/SKILL.md
Versions recorded
1
Latest version
git:20261117.080857b, committed Nov 17, 2026
Size
2,493 bytes
Repository stars
8
License
MIT

Write, review, or troubleshoot agent instructions and skills. Use for global rules, AGENTS.md, skill entrypoints and references, configuration, plugins, or hooks. Read Claude-specific references only when editing Claude Code files.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agent instruction surfaces

Choose the narrowest surface that matches who needs the instruction and when it applies. Keep reusable prose separate from mechanisms that enforce permissions or run code.

Read [Codex instruction discovery](references/codex-instructions.md) when placing global or repository guidance, diagnosing precedence, or checking which instructions loaded. Read [Codex skills](references/codex-skills.md) when creating, installing, enabling, or troubleshooting a Codex skill. For Claude Code work, read [Claude instruction loading](references/claude-loading.md) for `CLAUDE.md`, `AGENTS.md`, rules, imports, and memory, [Claude skills](references/claude-skills.md) for skill format and discovery, [Claude subagents](references/claude-subagents.md) for agent definitions, or [Claude plugins and output styles](references/claude-plugins.md) for bundle and style behavior.

Use these boundaries.

- Put durable, repository-specific conventions and commands in `AGENTS.md`.
- Use a skill for a reusable workflow that applies only to some tasks. Keep its description a concise trigger and place conditional detail behind linked references.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_iatux5bgorsa3erw/d335b8e1eb918040da9b2b19562a2004fefa7e3a06f9cbac50a1d15023bc64bd.json

Then /plugin install agent-docs@markdownregistry-iatux5bgorsa3erw in Claude Code. It installs git:20261117.080857b, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add dayfinggg/openai-codex-agent-skills/agent-docs@sha256:d335b8e1eb918040

The line at the top of this page pins the label git:20261117.080857b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_iatux5bgorsa3erw.svg)](https://markdownregistry.com/a/art_iatux5bgorsa3erw)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in dayfinggg/openai-codex-agent-skills/agent-docs since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of agent-docs from somewhere else? Ask it: where did my agent-docs come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Nov 17, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261117.080857b latest2026-11-17 080857b 2,493 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2493 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

dayfinggg/openai-codex-agent-skills · 8 stars · license MIT · pushed 2026-11-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_iatux5bgorsa3erw
GET https://markdownregistry.com/api/v1/resolve?ref=dayfinggg/openai-codex-agent-skills/agent-docs
GET https://markdownregistry.com/api/v1/blob/d335b8e1eb918040da9b2b19562a2004fefa7e3a06f9cbac50a1d15023bc64bd

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from dayfinggg/openai-codex-agent-skills

autonomous-run SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/autonomous-run/SKILL.md · Carry an explicitly unattended, headless, or multi-session task through its stated finish condition. Use when the user…
git:20261117.080857b · audit A · 8 stars
backend-api SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/backend-api/SKILL.md · Design or review HTTP API contracts, retries, idempotency, rate limits, pagination, deprecation, webhooks, and Stripe…
git:20261117.080857b · audit A · 8 stars
code-review SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/code-review/SKILL.md · Review a local diff or pull request for correctness, standards, and scope, or act on GitHub review feedback. Use for…
git:20261117.080857b · audit A · 8 stars
codebase-analysis SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/codebase-analysis/SKILL.md · Map unfamiliar code, trace callers and change impact, or plan a cross-file rename, removal, codemod, migration, or…
git:20261117.080857b · audit A · 8 stars
containers-iac SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/containers-iac/SKILL.md · Build and diagnose Docker and Compose images, Kubernetes manifests, Terraform or OpenTofu configuration, and…
git:20261117.080857b · audit C · 8 stars
database SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/database/SKILL.md · Guides safe, current database work on any SQL or NoSQL engine, with detailed rules for PostgreSQL and MySQL. Use it…
git:20261117.080857b · audit A · 8 stars
debugging SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/debugging/SKILL.md · Diagnosis loop for anything reported broken, throwing, failing, flaky, slow, or giving wrong output, including a user's…
git:20261117.080857b · audit A · 8 stars
frontend-ui SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/frontend-ui/SKILL.md · Design, implement, or review accessible web interfaces and visual styling. Use for HTML and CSS interactions, Tailwind…
git:20261117.080857b · audit A · 8 stars
git SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/git/SKILL.md · Structures git workflow and pull request bodies. Use it when committing, branching, pushing, resolving conflicts…
git:20261117.080857b · audit A · 8 stars
github-actions SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/github-actions/SKILL.md · Create, review, and debug GitHub Actions workflows and repository actions. Use for CI failures, workflow triggers and…
git:20261117.080857b · audit B · 8 stars
orchestration SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/orchestration/SKILL.md · Plan or coordinate explicitly authorized multi-agent work, including worker briefs, model selection, independent…
git:20261117.080857b · audit A · 8 stars
php SKILL.md skill
dayfinggg/openai-codex-agent-skills · codex/skills/php/SKILL.md · Gives current PHP practice for language features, Composer, static analysis, and tests, with Laravel and Symfony…
git:20261117.080857b · audit A · 8 stars

Every file in dayfinggg/openai-codex-agent-skills

Other files named agent-docs

agent-docs SKILL.md skill
birdsigh/skills · agent-docs/SKILL.md · Use when the user asks to init or bootstrap project or agent docs, create or add a README, CLAUDE.md, or AGENTS.md, add…
git:20260814.edbff2b · audit A · 3 stars

Browse by kind, by grade A, or by owner.