Codex Sub-Agent

Codex Sub-Agent is a skill for Claude Code, Codex from dante01yoon/codex-mcp-bridge. It costs 35 tokens per session (811 once invoked), scanned A, original, MIT.

A workflow that sends tasks to another Codex agent through a connection between tools. It chooses how to send the task based on whether the job needs an answer, code reading, or file changes.

In plain words
What is it for?
Use it to delegate questions, code analysis, code generation, and file-editing work to Codex while supplying relevant project context.
Why use it?
It removes the need to manually choose the right delegation method, permissions, and output format for each task.

Skill for Claude CodeCodex

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/dante01yoon/codex-mcp-bridge/codex-subagent
Any agent
npx skills add dante01yoon/codex-mcp-bridge --skill codex-subagent
Clone the repo
git clone --depth 1 https://github.com/dante01yoon/codex-mcp-bridge

Made for: Claude Code, 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 Sub-Agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/dante01yoon/codex-mcp-bridge/codex-subagent.svg)](https://agentmods.dev/skills/dante01yoon/codex-mcp-bridge/codex-subagent)
Your own site
<a href="https://agentmods.dev/skills/dante01yoon/codex-mcp-bridge/codex-subagent"><img src="https://agentmods.dev/badge/skills/dante01yoon/codex-mcp-bridge/codex-subagent.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 811 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00035 $0.00811
Opus 5 $0.00017 $0.00405
Sonnet 5 $0.00007 $0.00162
Haiku 4.5 $0.00003 $0.00081

Measured 5d ago against content hash a37517b2af47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Codex Sub-Agent 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 5d ago.

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.

examples/claude-skills/codex-subagent/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are now operating in Codex sub-agent mode. Delegate the task below to Codex via the MCP bridge and orchestrate the result.

Delegation Rules

  1. Analyze the task to determine the appropriate mode:

    • If the task is a question or analysis → use consult_codex with sandbox: "read-only"
    • If the task requires reading existing code → use consult_codex_with_stdin with sandbox: "read-only"
    • If the task requires creating or modifying files → use consult_codex or consult_codex_with_stdin with sandbox: "workspace-write"
  2. Gather context before delegating:

    • Read any files mentioned or implied by the task
    • Check the project structure if the task involves creating new files
    • Identify relevant types, interfaces, or conventions from existing code
  3. Construct the Codex prompt carefully:

    • Be explicit about what output format you expect
    • Include all necessary context (Codex has NO memory of this conversation)
    • Specify constraints: language, framework, style conventions
    • If the task is complex, break it into steps and make multiple Codex calls sequentially
  4. Process the result:

    • Validate the Codex output before presenting or applying it
    • If Codex returns code, check for obvious issues (syntax, imports, types)
    • If the result is unsatisfactory, refine the prompt and re-delegate
    • Show the user what Codex produced and what you did with it

Tool Selection Guide

Task Type              → Tool                           → Sandbox
─────────────────────────────────────────────────────────────────
Question / research    → consult_codex                  → read-only
Code review            → consult_codex_with_stdin       → read-only
Code explanation       → consult_codex_with_stdin       → read-only
Test generation        → consult_codex_with_stdin       → read-only
Bug fix                → consult_codex_with_stdin       → workspace-write
Refactoring            → consult_codex_with_stdin       → workspace-write
New code generation    → consult_codex                  → workspace-write
Multi-file changes     → consult_codex_with_stdin (×N)  → workspace-write

Read the full file on GitHub · 84 lines

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. 5d ago First seen · 84 lines · 35 tokens per session scan A a37517b2af47

Subscribe to this mod's changes

Codex Sub-Agent is a skill published in the GitHub repository dante01yoon/codex-mcp-bridge (2 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 811 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens