agentleFS
Sign inStart free
cukascukas/claudes-ai-buddies/skills/codex/SKILL.md

codex

Skill9 starsChanged 8 months agoMITView on GitHub

Ask OpenAI Codex anything — brainstorm, delegate tasks, get a second opinion

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

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 111 edited versions we read keep these.

  • 3

    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:

    Run the wrapper script via Bash.

    line 12
  2. Distinctive:

    Determine the working directory: Default to the current project root.

    line 26
  3. Distinctive:

    Show Codex's raw response directly: Use this format — show their actual words, don't paraphrase or summarize:

    line 29
  4. Distinctive:

    Add your own take only if asked: If the user wants a comparison or synthesis, add it after Codex's response.

    line 36

“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 — Peer AI via OpenAI Codex

You have access to OpenAI's Codex CLI as a peer AI. Use it to brainstorm, delegate tasks, get second opinions, or ask questions from a different AI perspective.

How to invoke

Run the wrapper script via Bash. IMPORTANT: Codex regularly takes 3-6 minutes for non-trivial tasks. You MUST set the Bash tool's timeout parameter to 420000 (7 minutes) to prevent Claude Code from killing the process before Codex finishes.

bash "${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.sh" \
  --prompt "YOUR PROMPT HERE" \
  --cwd "/path/to/relevant/directory" \
  --mode exec

Then read the output file path it prints and present the results to the user.

Step-by-step workflow

  1. Parse the user's request. The user says /codex "some prompt" or /codex followed by a question.
  2. Determine the working directory. Default to the current project root. If the user references a specific repo or directory, use that.
  3. Run codex-run.sh with --mode exec and the user's prompt via the Bash tool.
  4. Read the output file using the Read tool. The script prints the output file path to stdout.
  5. Show Codex's raw response directly. Use this format — show their actual words, don't paraphrase or summarize:
🔵 **Codex:**
> [their full response here, verbatim, as a blockquote]
  1. Add your own take only if asked. If the user wants a comparison or synthesis, add it after Codex's response. Otherwise, let Codex's voice stand on its own.

Options

FlagDefaultDescription
--prompt(required)The question or task for Codex
--cwdcurrent dirWorking directory for Codex
--modeexecAlways exec for this skill
--timeoutfrom config (360s)Max seconds to wait
--modelfrom configOverride the Codex model
--sandboxfull-autoSandbox mode: full-auto or suggest

Example invocations

  • /codex "What's the best way to implement a rate limiter in Go?"
  • /codex "Review this architecture: we have a React frontend calling a FastAPI backend with Redis caching"
  • /codex "Write a bash script that finds duplicate files by hash"
  • /codex "Debug this error: TypeError: Cannot read property 'map' of undefined"

Rules

  • Always use --ephemeral and --full-auto — these are hardcoded in the wrapper, never override them.
  • Never pass secrets or API keys in the prompt.
  • Respect timeouts — if Codex times out, tell the user and suggest a simpler prompt.
  • Frame the output clearly — the user should always know which AI produced which response.
  • Don't modify files based on Codex's suggestions without user confirmation.

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