agentleFS
Sign inStart free
malinskibeniaminmalinskibeniamin/skills/codex/SKILL.md

codex

Skill4 starsChanged 10 days agoMITView on GitHub

Delegate to GPT-6.1 Sol through the Codex CLI. Use for clear-spec implementation, independent review, computer use, investigation, data analysis, or token-heavy mechanical work.

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, 3 are distinctive, and 2 are 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.

  • 2

    Very specific

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

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

    When delegation is authorized, check once: codex exec -m gpt-6.1-sol -c 'model_reasoning_effort="xhigh"' "reply OK".

    line 8
  2. Very specific:

    Read config/model-routing.json.

    line 17
  3. Distinctive:

    Investigate/analyze: read-only compact report.

    line 29
  4. Distinctive:

    Use timeout/reference background pattern.

    line 38
  5. Distinctive:

    Verify citations, commands, and high-risk conclusions.

    line 39

“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

Host gate: Claude-hosted only. In native Codex, work inline unless the user explicitly requests delegation/parallel agents. Never start recursive codex exec; preserve selected model/reasoning and Codex config.

When delegation is authorized, check once: codex exec -m gpt-6.1-sol -c 'model_reasoning_effort="xhigh"' "reply OK". If unavailable, use a labeled clean-context Opus 5.5 xhigh review and disclose missing different-family coverage. Route only Opus 5.5 and GPT-6.1 Sol; block if neither is available.

Route

VariantUse
Sol, xhigh (gpt-6.1-sol; never max)preferred PR reviewer; explicitly selected execution, computer use, investigation
Opus 5.5, xhigh (claude-opus-5-5)daily driver, UI, plans, code, chores; labeled clean-context review fallback

Read config/model-routing.json; never infer quality from name/price. REFERENCE.md owns provider gates and CLI mechanics.

Prompt contract

Name repo/branch, objective, scope/exclusions, criteria, skill rules/exemplar, verification, evidence, stop. Send only local context/diff; exclude secrets. Steering payload: inline matched path rules and one exemplars/ file.

Modes

  • Implement: Sol xhigh; isolate concurrent writes in worktrees.
  • Review: Sol xhigh: codex exec -s read-only -m gpt-6.1-sol -c 'model_reasoning_effort="xhigh"'; P0-P3 evidence. No guessed quota-based effort changes.
  • Adversarial: Claude-hosted and authorized only; one lane, never verdict.
  • Computer use: name app/URL, states, evidence.
  • Investigate/analyze: read-only compact report.

PR reports: local by default; publishing needs separate, explicit user intent.

Workflow

  1. Pass host/authorization gate.
  2. Select quality-qualified config route.
  3. Write self-contained contract.
  4. Use timeout/reference background pattern.
  5. Verify citations, commands, and high-risk conclusions.

Coordinator owns architecture, synthesis, product, safety, final judgment. Codex models do not own user-facing UI/copy/API design by default; block if Opus is unavailable.

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