codex SKILL.md skillA

codex from pymodel/claude-architect is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add pymodel/claude-architect/codex@git:20261011.5f6078b

Pins git:20261011.5f6078b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
pymodel/claude-architect
Path
skills/codex/SKILL.md
Versions recorded
5
Latest version
git:20261011.5f6078b, committed Oct 11, 2026
First version recorded
Jul 28, 2026
Size
8,107 bytes
Repository stars
32
License
MIT

Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.

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

# Codex Skill Guide

Always present this skill as `/architect:codex`. Never show a shorter command.

## Trust boundary

`/architect:codex` is the direct, unverified lane: it runs `codex exec` against the user's checkout without an isolated worktree, frozen Candidate Artifact, or independent verification. Use it for direct CLI assistance when those controls are not required. Use `/architect:delegate` for the verified lane when changes need isolation, a frozen Candidate Artifact, independent verification, and controlled integration.

Only `/architect:delegate` produces a frozen, independently verified Candidate Artifact and drives review, decision, and guarded integration. This direct skill must never call itself verified or invoke those lifecycle tools.

## Running a Task
1. For a new session (resumes inherit the prior model/effort — see step 5), ask the user (via `AskUserQuestion`) which **model** AND which **reasoning effort** to use, in a **single prompt with two questions**. When the user expresses no preference, default to `gpt-6.1-sol` at `high`.
   - **Model** — default `gpt-6.1-sol`:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add pymodel/claude-architect/codex@sha256:1ace6767fbf4521a

The line at the top of this page pins the label git:20261011.5f6078b, 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_tu2khfhtzughhaa6.svg)](https://markdownregistry.com/a/art_tu2khfhtzughhaa6)

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

Versions

The registry has recorded 5 versions of this file, between Jul 28, 2026 and Oct 11, 2026, about one every 19 days.

versioncommittedcommitsizeaudit
git:20261011.5f6078b latest2026-10-11 5f6078b 8,107 BA view · diff
git:20261010.2be6b562026-10-10 2be6b56 8,135 BA view · diff
git:20260728.633ffd32026-07-28 633ffd3 7,947 BA view · diff
git:20260728.88cf2b52026-07-28 88cf2b5 7,641 BA view · diff
git:20260728.9b3a08d2026-07-28 9b3a08d 7,959 BA view

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 (8107 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

pymodel/claude-architect · 32 stars · license MIT · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tu2khfhtzughhaa6
GET https://markdownregistry.com/api/v1/resolve?ref=pymodel/claude-architect/codex
GET https://markdownregistry.com/api/v1/blob/1ace6767fbf4521a4048b897b4def247e445336af897d605287b3d7d0cef73fb

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 pymodel/claude-architect

CLAUDE.md@.claude CLAUDE.md file
pymodel/claude-architect · .claude/CLAUDE.md
git:20261011.5f6078b · audit A · 32 stars
AGENTS.md AGENTS.md file
pymodel/claude-architect · AGENTS.md
git:20261012.e3586c8 · audit A · 32 stars
delegate SKILL.md skill
pymodel/claude-architect · skills/delegate/SKILL.md · Let Claude Architect route a versioned implementation spec through the trusted MCP runtime, independently review the…
git:20261011.5f6078b · audit A · 32 stars
subagent-driven-delegation SKILL.md skill
pymodel/claude-architect · skills/subagent-driven-delegation/SKILL.md · Execute an implementation plan with the Superpowers subagent-driven-development loop while every task is implemented by…
git:20261011.5f6078b · audit A · 32 stars

Every file in pymodel/claude-architect

Other files named codex

codex SKILL.md skill
garrytan/gstack · codex/SKILL.md · OpenAI Codex CLI wrapper — three modes. (gstack)
v1.0.0 · audit A · 136,966 stars
codex SKILL.md skill
dzhng/skills · skills/engineering/codex/SKILL.md · Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second…
git:20261015.f6819ca · audit A · 1,377 stars
codex SKILL.md skill
taracodlabs/aiden · skills/codex/SKILL.md · Delegate coding tasks to OpenAI Codex CLI
v1.0.0 · audit A · 859 stars
codex SKILL.md skill
notque/vexjoy-agent · skills/meta/codex/SKILL.md · Run benchmark-selected GPT-5.6 work through the Codex CLI.
git:20260922.5ea2099 · audit A · 442 stars
codex SKILL.md skill
giuseppe-trisciuoglio/developer-kit · plugins/developer-kit-tools/skills/codex/SKILL.md · Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex…
git:20260307.7eaf6d6 · audit A · 359 stars
codex SKILL.md skill
majiayu000/spellbook · skills/codex/SKILL.md · Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis…
git:20261007.a10192c · audit A · 288 stars
codex SKILL.md skill
yan-labs/yan-skills · codex/SKILL.md · 当用户明确要求直接操作 Codex CLI 作为后台代理(自选 sandbox、codex review、apply、resume 等原生命令,或用 git worktree 并行布置多个…
git:20260930.3f793f3 · audit A · 225 stars
codex SKILL.md skill
dzhng/duet-agent · .agents/skills/codex/SKILL.md · Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second…
git:20261020.37d28d9 · audit A · 50 stars

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