codex-supervision

codex-supervision is a skill for Codex from ltczding-gif/agent-supervision-skills. It costs 67 tokens per session (5,193 once invoked), scanned A, a copy of codex-supervision, MIT.

A set of PowerShell scripts for assigning code review, adversarial review, or substantial rescue work to the local Codex command-line tool, then checking its results.

In plain words
What is it for?
Use it from Claude Desktop to set up Codex, run delegated coding tasks, capture their output, and independently verify the result.
Why use it?
It avoids trusting delegated work without inspecting the changes, saved artifacts, and claims made about them.

Skill for Codex

Written for Codex: runs codex exec. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it from Claude Desktop to set up Codex, run delegated coding tasks, capture their output, and independently verify the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ltczding-gif/agent-supervision-skills/codex-supervision
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ltczding-gif/agent-supervision-skills --skill codex-supervision
Clone the repo
git clone --depth 1 https://github.com/ltczding-gif/agent-supervision-skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for codex-supervision

README.md
[![agentmods](https://agentmods.dev/badge/skills/ltczding-gif/agent-supervision-skills/codex-supervision/github.svg)](https://agentmods.dev/skills/ltczding-gif/agent-supervision-skills/codex-supervision)
Your own site
<a href="https://agentmods.dev/skills/ltczding-gif/agent-supervision-skills/codex-supervision"><img src="https://agentmods.dev/badge/skills/ltczding-gif/agent-supervision-skills/codex-supervision/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for codex-supervision

Your own site · 80×15
<a href="https://agentmods.dev/skills/ltczding-gif/agent-supervision-skills/codex-supervision"><img src="https://agentmods.dev/badge/skills/ltczding-gif/agent-supervision-skills/codex-supervision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,193 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.05193
Opus 5 $0.00034 $0.02596
Sonnet 5 $0.00013 $0.01039
Haiku 4.5 $0.00007 $0.00519

Measured 10d ago against content hash 659c6ef68e66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

codex-supervision scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/codex-list-sessions.ps1, scripts/codex-review.ps1, scripts/codex-setup.ps1, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to codex-supervision — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

codex-supervision/SKILL.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Supervision

Hand work to the local codex CLI and supervise the result — read what Codex actually did, inspect artifacts, verify claims, only then answer the user.

Supervision, not blind delegation.

This skill exists because the official openai/codex-plugin-cc is a Claude Code plugin, and Claude Desktop (consumer chat client) does not load plugins. The skill provides the essential capability via PowerShell wrapper scripts the model invokes through its shell tool.

Requirements

  • PowerShell 7+ (pwsh.exe). Uses ProcessStartInfo.ArgumentList and Process.Kill(bool) which are .NET Core 3+ only — Windows PowerShell 5.1 will not work. codex-setup.ps1 reports the detected version and refuses to mark ready=true on older hosts.
  • Node.js 18.18+ (codex CLI requirement)
  • codex CLI 0.128+ on PATH, at $env:CODEX_PATH, or at %USERPROFILE%\bin\codex.cmd
  • A ChatGPT subscription or OpenAI API key for codex authentication

What this skill provides

PowerShell scripts under scripts/:

  • common.ps1 — codex resolution, env hygiene, async I/O, timeout, artifact capture
  • codex-setup.ps1 — verify codex CLI version + login + writable state dir
  • codex-review.ps1 — non-interactive code review (normal or adversarial) via codex exec review
  • codex-task.ps1 — delegate an arbitrary task to codex (rescue equivalent)
  • codex-list-sessions.ps1 — inspect prior runs

These scripts:

  • require a locally installed codex CLI on PATH, at $env:CODEX_PATH, or at %USERPROFILE%\bin\codex.cmd
  • read/write UTF-8; set Console.OutputEncoding to UTF-8 to survive Chinese-locale Windows
  • run codex non-interactively (codex exec / codex exec review) with async stdout/stderr reads — no pipe-buffer deadlock
  • enforce a -TimeoutSec and kill codex if it hangs
  • pass -Base / -Uncommitted / -Title through to the native review subcommand (codex does the git diff scoping itself)
  • default to read-only sandbox; only escalate to workspace-write with -Write, or danger-full-access with -DangerousFullAccess
  • always write last-prompt.txt, last-response.txt, stderr.log, session.json to the session dir

Read the full file on GitHub · 392 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 392 lines · 67 tokens per session scan A 659c6ef68e66

Subscribe to this mod's changes

codex-supervision is a skill published in the GitHub repository ltczding-gif/agent-supervision-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 5,193 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to codex-supervision, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

agentbro-pr-merge

Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.

shirenchuang/agentbro · 38 tokens

codegraph

Use for repo structure, symbol navigation, dependency analysis, duplicate triage, and PR impact review when plain text search is too shallow.

lzehrung/codegraph · 30 tokens

claude-supervision

Use when the user wants to delegate work to the local Claude Code CLI (claude --print, claude --bg, claude ultrareview) — substantive tasks, multi-turn resume, structured output, multi-agent code review, background sessions — and then independently verify what Claude did. Useful from Codex / Kimi / any agent that…

drippy-passport968/agent-supervision-skills · 117 tokens

codex-supervision

Use when the user wants Claude to delegate work to the local Codex CLI — code review, adversarial review, or substantive rescue tasks — and then independently verify what Codex did. Works in Claude Desktop (no plugin system required); wraps codex exec as PowerShell scripts and keeps run artifacts on disk.

drippy-passport968/agent-supervision-skills · 67 tokens

skill-author

Package and validate an existing skill draft for AutoVault when its frontmatter, resources, capabilities, or admission result need review.

autoworks-ai/autovault · 28 tokens

code-review

Systematic code review SOP covering correctness, security, performance, and maintainability — plus GitHub PR review workflow (diff, inline comments, approve via gh/REST).

furkangonel/cowrangler · 37 tokens