agentleFS
Sign inStart free
longranger2longranger2/claude-gpt-workflow/codex/SKILL.md

codex

Skill76 starsChanged 8 months agoMITView on GitHub

Delegate coding tasks to Codex CLI for execution, or discuss implementation approaches with it. CodeX is a cost-effective, strong coder — great for batch refactoring, code generation, multi-file changes, test writing, and multi-turn implementation tasks. Use when the plan is clear and needs hands-on coding. Claude handles architecture, strategy, copywriting, and ambiguous problems better.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 106 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    ONLY interact with CodeX through the bundled shell script.

    line 12
  2. Distinctive:

    Run the script ONCE per task.

    line 13
  3. Distinctive:

    Do NOT read or inspect the script source code.

    line 14
  4. Very specific:

    ALWAYS quote file paths containing brackets, spaces, or special characters when passing to the script (e.g.

    line 15
  5. Very specific:

    Never paste file contents into the prompt: Use --file to point CodeX to key files — it reads them directly.

    line 17
  6. Very specific:

    Read the file at output_path to get CodeX's response.

    line 56
  7. Distinctive:

    Call CodeX when at least one of these is true:

    line 60
  8. Very specific:

    Run the script with a clear, concise task description.

    line 73
  9. Distinctive:

    Read the output — CodeX executes changes and reports what it did.

    line 75

“Common” is measured: kept by at least 6 in 10 of the 106 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 — Your Codex Coding Partner

Delegate coding execution to Codex CLI. CodeX turns clear plans into working code.

Critical rules

  • ONLY interact with CodeX through the bundled shell script. NEVER call codex CLI directly.
  • Run the script ONCE per task. If it succeeds (exit code 0), read the output file and proceed. Do NOT re-run or retry.
  • Do NOT read or inspect the script source code. Treat it as a black box.
  • ALWAYS quote file paths containing brackets, spaces, or special characters when passing to the script (e.g. --file "src/app/[locale]/page.tsx"). Unquoted [...] triggers zsh glob expansion.
  • Keep the task prompt focused. Aim for under ~500 words. Describe WHAT to do and key constraints, not step-by-step HOW. CodeX is an autonomous agent with full workspace access — it reads files, explores code, and figures out implementation details on its own.
  • Never paste file contents into the prompt. Use --file to point CodeX to key files — it reads them directly. Duplicating file contents in the prompt wastes tokens and adds no value.
  • Don't reference or describe the SKILL.md itself in the prompt. CodeX doesn't need to know about this skill's configuration.

How to call the script

The script path is:

~/.claude/skills/codex/scripts/ask_codex.sh

Minimal invocation:

~/.claude/skills/codex/scripts/ask_codex.sh "Your request in natural language"

With file context:

~/.claude/skills/codex/scripts/ask_codex.sh "Refactor these components to use the new API" \
  --file src/components/UserList.tsx \
  --file src/components/UserDetail.tsx

Multi-turn conversation (continue a previous session):

~/.claude/skills/codex/scripts/ask_codex.sh "Also add retry logic with exponential backoff" \
  --session <session_id from previous run>

The script prints on success:

session_id=<thread_id>
output_path=<path to markdown file>

Read the file at output_path to get CodeX's response. Save session_id if you plan follow-up calls.

Decision policy

Call CodeX when at least one of these is true:

  • The implementation plan is clear and needs coding execution.
  • The task involves batch refactoring, code generation, or repetitive changes.
  • Multiple files need coordinated modifications following a defined pattern.
  • You want a practitioner's perspective on whether a plan is feasible.
  • The task is cost-sensitive and doesn't require deep architectural reasoning.
  • Writing or updating tests based on existing code.
  • Simple-to-moderate bug fixes where the root cause is identified.

Workflow

  1. Design the solution and identify the key files involved.
  2. Run the script with a clear, concise task description. Tell CodeX the goal and constraints, not step-by-step implementation details — it figures those out itself. For discussion, use a question-oriented task with --read-only.
  3. Pass relevant files with --file (2-6 high-signal entry points; CodeX has full workspace access and will discover related files on its own).
  4. Read the output — CodeX executes changes and reports what it did.
  5. Review the changes in your workspace.

For multi-step projects, use --session <id> to continue with full conversation history. For independent parallel tasks, use the Task tool with run_in_background: true.

Options

  • --workspace <path> — Target workspace directory (defaults to current directory).
  • --file <path> — Point CodeX to key entry-point files (repeatable, workspace-relative or absolute). Don't duplicate their contents in the prompt.
  • --session <id> — Resume a previous session for multi-turn conversation.
  • --model <name> — Override model (default: uses Codex config).
  • --reasoning <level> — Reasoning effort: low, medium, high (default: medium). Use high for code review, debugging, complex refactoring, or root cause analysis.
  • --sandbox <mode> — Override sandbox policy (default: workspace-write via full-auto).
  • --read-only — Read-only mode for pure discussion/analysis, no file changes.

Download now (ZIP)

  • Other versions130 projects use a version of this.

    Word for word · 1

    1. AshlynYang-dev/claude-code-codex-skill★ 1100% same

    Edited · 0

    None found.

    Wrote their own version · 129

    1. NousResearch/hermes-agent★ 259ksame name
    2. garrytan/gstack★ 139ksame name
    3. dzhng/jevgrep★ 3.1ksame name
    4. ispc/ispc★ 3ksame name
    5. bergside/awesome-design-skills★ 2.9ksame name
    6. dataplat/dbatools★ 2.9ksame name
    7. Lilac-Labs/gini-agent★ 1.9ksame name
    8. Open-Curiosity/gini-agent★ 1.9ksame name
    9. dzhng/skills★ 1.4ksame name
    10. clice-io/clice★ 1.4ksame name

    119 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects 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

    • 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

    • math-incSkill

      pokemon-player

      Play Pokemon games autonomously via headless emulation. Starts a game server, reads structured game state from RAM, makes strategic decisions, and sends button inputs — all from the terminal.

      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

    • 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

    • +1 more from math-inc
  • In this repository2 other files it gives its agents.

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