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.
npx agentmods add skills/ching-kuo/claude-codex/codex-mcpnpx skills add ching-kuo/claude-codex --skill codex-mcpgit clone --depth 1 https://github.com/ching-kuo/claude-codexWrote 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.
[](https://agentmods.dev/skills/ching-kuo/claude-codex/codex-mcp)<a href="https://agentmods.dev/skills/ching-kuo/claude-codex/codex-mcp"><img src="https://agentmods.dev/badge/skills/ching-kuo/claude-codex/codex-mcp.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.00508 |
| Opus 5 | $0.00022 | $0.00254 |
| Sonnet 5 | $0.00009 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
codex-mcp 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 4d 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.
What it actually says
Codex MCP Usage Guide
Tools
| Tool | Purpose |
|---|---|
mcp__codex__codex |
Start a new Codex session. Returns a threadId + response. |
mcp__codex__codex-reply |
Continue an existing session using threadId. |
Session Management
Codex sessions are stateful via threadId. Always:
- Save the
threadIdfrom the firstmcp__codex__codexcall - Use
mcp__codex__codex-replywith that threadId for all follow-ups - Never start a new session when continuing the same task — context carries forward
Key Parameters
sandbox
| Mode | When to Use |
|---|---|
read-only |
Plan review, code audit, Q&A — Codex reads but cannot write files |
workspace-write |
Implementation — Codex writes files in the project directory |
approval-policy
| Policy | When to Use |
|---|---|
never |
Review-only tasks where no shell commands are needed |
on-failure |
Implementation — auto-approve commands, intervene on errors |
developer-instructions
Inject a persona or constraints into Codex without polluting the main prompt.
Always include: "Be concise. Do not include your reasoning process in the response. Only output the result."
Prompting Best Practices
- Termination signals: Ask Codex to reply "APPROVED" or "CHANGES NEEDED" — gives clear loop control
- Feedback verbatim: When sending review feedback via codex-reply, quote specific issues exactly. Do not summarize.
- Concise responses: Always instruct Codex to be concise via developer-instructions to save tokens
- Max iterations: Always enforce a hard cap (default: 5) on review loops
stderr Suppression
The MCP server config uses 2>/dev/null at the process level.
Individual tool calls do NOT need stderr suppression — MCP returns structured JSON-RPC responses only.
See reference.md for detailed examples and patterns.
What ships with it
1 file 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.
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.
- 4d ago First seen · 53 lines · 43 tokens per session scan A d95235921943
codex-mcp is a skill published in the GitHub repository ching-kuo/claude-codex (23 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 508 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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.
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…