AGENTS.md@codexA

AGENTS.md@codex from dennisonbertram/developer-skill-pack is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add dennisonbertram/developer-skill-pack/codex/AGENTS.md@git:20260523.7ded56a

Pins git:20260523.7ded56a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
dennisonbertram/developer-skill-pack
Path
codex/AGENTS.md
Versions recorded
1
Latest version
git:20260523.7ded56a, committed May 23, 2026
Size
1,236 bytes
Repository stars
24
License
MIT

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 Workflow — Codex CLI

These rules apply to all agent work in this repository when using OpenAI Codex CLI.

## TDD Is Non-Negotiable

Every implementation change must follow Red-Green-Refactor:

1. **RED** — Write the failing test first and run it.
2. **GREEN** — Make the smallest change that passes.
3. **REFACTOR** — Clean up while the tests stay green.

Never modify `src/` before writing the corresponding test.

## Before You Start

1. Read `docs/context/repo-practices.md` — durable patterns and rules
2. Read `docs/context/known-issues.md` — known bugs and workarounds
3. Run the baseline test command for the surface you're about to change

## Branch Discipline

- Never push directly to `main`
- One issue per PR, one branch per issue
- All changes via PR with CI passing

## Worktree Isolation

Every implementation task happens in a git worktree:

```bash
git fetch origin
git worktree add -b <feature-branch> /tmp/<project>-<name> origin/main
cd /tmp/<project>-<name>
<package-manager> install
```

## Definition Of Done

1. Failing test observed first
2. Targeted test suite green
3. Adjacent regression suite green
4. Typecheck passes
5. Full test suite passes
6. Docs updated
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add dennisonbertram/developer-skill-pack/codex/AGENTS.md@sha256:4a35a67fff392eef

The line at the top of this page pins the label git:20260523.7ded56a, 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_eyebxlezyrc5jfaq.svg)](https://markdownregistry.com/a/art_eyebxlezyrc5jfaq)

2 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 dennisonbertram/developer-skill-pack/codex/AGENTS.md 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 AGENTS.md from somewhere else? Ask it: where did my AGENTS.md 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 May 23, 2026.

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

versioncommittedcommitsizeaudit
git:20260523.7ded56a latest2026-05-23 7ded56a 1,236 BA view
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  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (1236 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

dennisonbertram/developer-skill-pack · 24 stars · license MIT · pushed 2026-11-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_eyebxlezyrc5jfaq
GET https://markdownregistry.com/api/v1/resolve?ref=dennisonbertram/developer-skill-pack/codex/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/4a35a67fff392eef4e537d63143563123227a944110224f0c628495e84aa6791

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: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from dennisonbertram/developer-skill-pack

chief SKILL.md skill
dennisonbertram/developer-skill-pack · skills/chief/SKILL.md · Turn this session into the chief: it coordinates your OTHER Claude Code sessions on this machine. It shows what each…
v0.1.0 · audit A · 24 stars
coordinator SKILL.md skill
dennisonbertram/developer-skill-pack · skills/coordinator/SKILL.md · Launch the coordinator — a pure-delegation control plane that plans, delegates, reviews, and learns. Use when asked to…
v1.0.0 · audit A · 24 stars
debug SKILL.md skill
dennisonbertram/developer-skill-pack · skills/debug/SKILL.md · Deterministic 7-phase debugging workflow — symptom capture, git archaeology, reproduce with a targeted test, log…
v1.0.0 · audit A · 24 stars
deploy-check SKILL.md skill
dennisonbertram/developer-skill-pack · skills/deploy-check/SKILL.md · Instrument a frontend with version fingerprinting (meta tag + /__version endpoint) so LLM-based testing can verify the…
v1.0.0 · audit A · 24 stars
free-web-search SKILL.md skill
dennisonbertram/developer-skill-pack · skills/free-web-search/SKILL.md · Free web search for AI agents over MCP, with no sign-in and no API key. Use when you need current information from the…
v1.0.0 · audit A · 24 stars
mine-transcripts SKILL.md skill
dennisonbertram/developer-skill-pack · skills/mine-transcripts/SKILL.md · Sweep sub-agent JSONL transcripts for novel learnings and promote the strongest to durable docs. Use when asked to…
v1.0.0 · audit A · 24 stars
regression-guard SKILL.md skill
dennisonbertram/developer-skill-pack · skills/regression-guard/SKILL.md · Post-fix test-coverage analysis. Reviews a just-landed fix, generates targeted unit and regression tests, audits how…
v1.0.0 · audit A · 24 stars
research-spike SKILL.md skill
dennisonbertram/developer-skill-pack · skills/research-spike/SKILL.md · Time-boxed research before adopting a library, API, architecture, or provider. Use when asked to 'research', 'compare…
v1.0.0 · audit A · 24 stars
setup-repo SKILL.md skill
dennisonbertram/developer-skill-pack · skills/setup-repo/SKILL.md · Scaffold a new repository with GitHub issue templates, PR template, development process docs, TDD workflow, hooks, and…
v1.0.0 · audit A · 24 stars
ux-auto-improve SKILL.md skill
dennisonbertram/developer-skill-pack · skills/ux-auto-improve/SKILL.md · Improve one section of an app end to end, in a loop: a cheap reviewer critiques the section (UX, DRY, modularity…
v0.1.0 · audit A · 24 stars
ux-flow-native SKILL.md skill
dennisonbertram/developer-skill-pack · skills/ux-flow-native/SKILL.md · Critique a native macOS/iOS app's user experience for simplicity, clarity, and redundancy. Measures friction against…
v0.1.0 · audit A · 24 stars
ux-flow SKILL.md skill
dennisonbertram/developer-skill-pack · skills/ux-flow/SKILL.md · Critique the app's user experience for simplicity, clarity, and redundancy. For each core journey asks 'how could this…
v0.1.0 · audit A · 24 stars

Every file in dennisonbertram/developer-skill-pack

Other files named AGENTS.md@codex

AGENTS.md@codex AGENTS.md file
tobihagemann/turbo · codex/AGENTS.md
git:20261112.b0e3965 · audit A · 423 stars
AGENTS.md@codex AGENTS.md file
acogood/diffmode_free · codex/AGENTS.md
git:20260810.c175a4d · audit A · 166 stars
AGENTS.md@codex AGENTS.md file
kamioj/spec-workflow · codex/AGENTS.md
git:20261112.dd2a4dd · audit A · 21 stars
AGENTS.md@codex AGENTS.md file
darkworldcoder/market-mirror · codex/AGENTS.md
git:20261110.2ffb39f · audit A · 16 stars
AGENTS.md@codex AGENTS.md file
nelson820125/iforgeai · codex/AGENTS.md
git:20260410.f993f6d · audit B · 13 stars
AGENTS.md@codex AGENTS.md file
yichen-zju/claude-for-research · codex/AGENTS.md
git:20261021.4e8d8a8 · audit A · 12 stars
AGENTS.md@codex AGENTS.md file
dongduong2001/pudo-code-system · codex/AGENTS.md
git:20260519.13df8aa · audit A · 5 stars
AGENTS.md@codex AGENTS.md file
jgwill/miadi-orchestration-kit · codex/AGENTS.md
git:20261114.4cf85c1 · audit A · 4 stars

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