agentmods.dev

Codex

A skill for directing the Codex command-line program as a separate coding and analysis assistant. It controls how Codex runs, including its model, reasoning, searches, tools, and execution limits.

In plain words
What is it for?
Use it to launch Codex for coding, analysis, web searches, reviews, or parallel work sessions.
Why use it?
It helps another assistant delegate work to Codex with clear control over what Codex can use and how it runs.

Skill for Claude CodeCodex

2 4d ago B scan 64 tokens original Apache-2.0
View the source file gitguffaw/codex-router
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.

agentmods
npx agentmods add skills/gitguffaw/codex-router/codex
Any agent
npx skills add gitguffaw/codex-router --skill codex
Clone the repo
git clone --depth 1 https://github.com/gitguffaw/codex-router

Made for: Claude Code, Codex.

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,458 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found 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 $0.00064 $0.02458
Opus 5 $0.00032 $0.01229
Sonnet 5 $0.00013 $0.00492
Haiku 4.5 $0.00006 $0.00246

Measured yesterday against content hash 285ef95320e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

Codex scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Configured model in `~/.codex/config.toml`: `gpt-5.5`
plugins/codex-router/policy/Codex/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex

Purpose

Use this skill to make Claude operate Codex the way a strong human operator would: pick the right outcome mode, choose the launch surface, set model and reasoning explicitly when needed, and direct inner Codex to use its own search, MCP, plugin, skill, and tool surfaces.

Boundary

  • Outer Claude and inner Codex are different tool layers.
  • If the task says to use Codex search, Codex MCP, Codex plugins, Codex skills, Codex marketplace, or Codex-native tools, satisfy that inside the launched Codex session.
  • Do not silently substitute Claude's own web tools or MCP tools when the request is explicitly about inner Codex capability.
  • Use Claude's own tools only for maintaining this skill, validating local Codex state, or when inner Codex capability is unavailable and that fallback is explicitly acceptable.

Last Verified

  • Verified against codex-cli 0.124.0.
  • Verified on 2026-04-24.

Last Observed Local State

  • Configured model in ~/.codex/config.toml: gpt-5.5
  • Configured reasoning effort in ~/.codex/config.toml: xhigh
  • Configured service tier in ~/.codex/config.toml: fast
  • Observed listed model IDs from codex debug models on this machine:
    • gpt-5.5
    • gpt-5.4
    • gpt-5.4-mini
    • gpt-5.3-codex
    • gpt-5.3-codex-spark
    • gpt-5.2
  • Observed inner tool surface on this machine:
    • context7
    • playwright
    • figma
    • linear
    • cloudflare-api
    • computer-use
  • Treat these as machine-local observations, not universal Codex contract.

Preflight

When model choice, reasoning, tool availability, docs source, or feature availability matters, probe current Codex state first.

  • codex --help
  • codex <cmd> --help
  • codex debug models
  • codex mcp list
  • codex features list
  • ~/.codex/config.toml
  • If codex debug models is unavailable, inspect ~/.codex/config.toml and ~/.codex/models_cache.json as fallback local state.
  • For OpenAI/Codex docs work, prefer openaiDeveloperDocs if available. If not, prefer official OpenAI docs through Codex web search before falling back to third-party docs MCPs.

Read the full file on GitHub · 202 lines

Files

What ships with it

9 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. yesterday First seen · 202 lines · 64 tokens per session scan B 285ef95320e7

Subscribe to this mod's changes

Codex is a skill published in the GitHub repository gitguffaw/codex-router (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 64 tokens to every session and 2,458 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code reviewData and AIResearchclaude-codeclaude-code-plugincodexopenai-codex
Related

Other skills, from other repositories

codex-delegate

Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" …

amElnagdy/delegate-skills · 155 tokens

commandcode-delegate

Delegate a coding task to the Command Code CLI (cmd) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Command Code — phrasings like "have Command Code do X", "delegate this to commandcode", "run it through cmd", or "use Command Code…

amElnagdy/delegate-skills · 123 tokens

opencode-delegate

Delegate a coding task to the OpenCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to OpenCode — phrasings like "have OpenCode do X", "delegate this to OpenCode", "run it through OpenCode", or "use OpenCode to…

amElnagdy/delegate-skills · 136 tokens

warp-delegate

Delegate a coding task to the Warp Agent CLI (oz) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Warp - phrasings like "have Warp implement X", "delegate this to the Warp CLI", "run it through Warp", "use oz to…

amElnagdy/delegate-skills · 144 tokens

zcode-delegate

Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to ZCode — phrasings like "have ZCode do X", "delegate this to ZCode", "run it through ZCode", or "use ZCode to implement/fix/refactor" — or…

amElnagdy/delegate-skills · 124 tokens

agy-delegate

Delegate a coding task to the Google Antigravity CLI (agy) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use…

amElnagdy/delegate-skills · 132 tokens