agentleFS
ericpardeeericpardee/agent-files/skills/skill-codex/SKILL.md

codex

Skill3 starsChanged 4 months agoMITView on GitHub

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

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

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 111 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Do not pass -m. ~/.codex/config.toml sets the default model.

    line 13
  2. Very specific:

    Always redirect stdin from /dev/null.

    line 17

“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 CLI

Reference for driving codex exec correctly from an agent session. For a full review gate with a fix-or-rebut loop, use the codex-gate skill instead.

Invocation rules

  • Do not pass -m. ~/.codex/config.toml sets the default model; override it only when the user names a model. Pair reviews with -c model_reasoning_effort="xhigh" (options: none, minimal, low, medium, high, xhigh).
  • Always redirect stdin from /dev/null. codex exec appends stdin to the prompt, so without the redirect it blocks on an open terminal and looks like a slow reasoning pass until killed. The tell is empty stdout with Reading additional input from stdin... on stderr.
  • Append 2>/dev/null to hide thinking tokens (stderr). Show stderr only when debugging.
  • Sandbox: --sandbox read-only for reviews, workspace-write for edits, danger-full-access only for work that needs the network. --full-auto was removed (codex-cli 0.160 rejects it with unexpected argument); a workspace-write exec run edits without it. Ask before danger-full-access or --skip-git-repo-check unless the user already granted it.
  • -C <dir> runs from another directory; --skip-git-repo-check is needed outside a repository.
  • -i <file> attaches an image and takes a list of files, so it swallows a prompt placed after it (the run then fails with No prompt provided via stdin). Put the prompt before any -i flags, or repeat -i per file after the prompt.
  • Pass -o <file> when the final message must survive scrollback.

Reviews

codex exec review accepts a scope flag (--base <branch>, --commit <sha>, --uncommitted) or a custom prompt, never both; combining them fails arg parsing with the argument '--base <BRANCH>' cannot be used with '[PROMPT]' (codex-cli 0.146 through 0.154). So:

  • Codex's own review instructions on a scope: codex exec review --base main </dev/null 2>/dev/null
  • Your own instructions: plain codex exec with the scope stated in the prompt, for example codex exec --sandbox read-only "<instructions>. Review only the changes on this branch relative to main; see them with git diff main...HEAD." </dev/null 2>/dev/null

Resuming

codex exec resume --last "<prompt>" </dev/null 2>/dev/null continues the previous session with its original model, reasoning effort, and sandbox; do not pass configuration flags when resuming unless the user asks. After any run, tell the user the session can be resumed this way.

Quick reference

Use caseCommand
Review a branchcodex exec review --base main </dev/null 2>/dev/null
Review uncommitted workcodex exec review --uncommitted </dev/null 2>/dev/null
Review one commitcodex exec review --commit abc123 </dev/null 2>/dev/null
Review with your own instructionscodex exec --sandbox read-only "<instructions> Review only <scope>." </dev/null 2>/dev/null
Apply editscodex exec --sandbox workspace-write "Refactor ..." </dev/null 2>/dev/null
Resumecodex exec resume --last "continue with ..." </dev/null 2>/dev/null
Another directorycodex exec -C /path --sandbox read-only "..." </dev/null 2>/dev/null

After a run

Summarize the outcome. When the output has actionable findings, offer to resume the session to apply them; do not apply or commit changes on the user's behalf without being asked. Stop and report when codex exits non-zero or returns partial results, and ask how to proceed.

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.