agentleFS
Sign inStart free
23jmo23jmo/jmo-skills/skills/codex/SKILL.md

codex

Skill9 starsChanged 33 days agoMITView on GitHub

Hand off a scoped implementation, code review, or technical second opinion to the OpenAI Codex CLI from Claude Code. Use when the user asks to delegate work to Codex or get an independent review.

135 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ios-sync, compare-screenshots and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • transitive-bullshitSkill

    compare-screenshots

    Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.

    Also in 5 projects that use this

  • dzhngSkill

    implement-spec-with-codex

    Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with Codex, or to run implement-spec with Codex as the implementer.

    Also in 4 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 7 projects that use this

  • math-incSkill

    minecraft-modpack-server

    Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

    Also in 5 projects that use this

  • +1 more from Saqlain-811

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 111 edited versions we read keep these.

  • 4

    Distinctive

    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
  1. Very specific:

    Check command -v codex and codex exec --help.

    line 13
  2. Distinctive:

    Read the repository instructions and inspect git status --short.

    line 14
  3. Distinctive:

    Write a focused prompt containing the user's task, relevant paths, constraints, and required checks.

    line 15
  4. Distinctive:

    Use the user's configured model.

    line 19
  5. Distinctive:

    Wait for completion and read the exit status and output.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 111 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Codex handoff

This is JMO's standalone handoff skill. It is not gstack's /codex skill and does not require gstack.

Prepare the task

  1. Check command -v codex and codex exec --help. If missing, direct the user to https://developers.openai.com/codex/cli/ and explain that they must install and sign in to Codex. Do not claim a handoff ran when the CLI is unavailable.
  2. Read the repository instructions and inspect git status --short. Identify the working directory, requested mode (review, advice, or implementation), allowed files, and acceptance criteria. Default to read-only review when the request does not authorize edits.
  3. Write a focused prompt containing the user's task, relevant paths, constraints, and required checks. Include enough context for a separate agent without passing credentials or unrelated private material. Tell Codex which files are already modified and to preserve those changes.

Run Codex

Use the user's configured model. Pass the prompt through stdin or a quoted heredoc, not interpolated shell text. Replace the example directory with the actual absolute project path:

codex exec --sandbox read-only --cd '/absolute/project/path' - <<'TASK'
Review the specified changes. Do not edit files. Report actionable findings with file locations, evidence, and uncertainty. Follow the repository's instructions.
TASK

For an authorized implementation, use --sandbox workspace-write and a prompt with the exact task, allowed files, and verification criteria. Do not use flags that bypass approvals or sandboxing. If the task cannot run within the current permissions, report that limitation.

Wait for completion and read the exit status and output. Do not let Claude and Codex edit the same files concurrently. For parallel work, use separate worktrees and explicit file ownership; integrate only after reviewing the resulting changes.

Verify and report

For a review, inspect the cited code and assess each finding before presenting it as confirmed. For implementation, inspect the diff and run the relevant checks. Report what Codex changed or found, what was verified, and any remaining failures. Do not automatically commit, push, or deploy unless that is part of the user's task.

Task: $ARGUMENTS

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free