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/shilong20/codexmcp/codexmcp-usingnpx skills add shilong20/codexmcp --skill codexmcp-usinggit clone --depth 1 https://github.com/shilong20/codexmcpWhat 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 | $0.00061 | $0.01302 |
| Opus 5 | $0.00030 | $0.00651 |
| Sonnet 5 | $0.00012 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
codexmcp-using 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodexMCP 使用指南
通过 MCP 调用 Codex CLI 执行编码任务。
工具一览
| 工具 | 类型 | 用途 |
|---|---|---|
codex |
阻塞 | 等待完成后返回结果（主推） |
codex_dispatch |
异步 | 立即返回，后台运行 |
codex_status |
查询 | 查询任务状态/进度/结果 |
codex_cancel |
控制 | 取消运行中的任务 |
快速参考
CallMcpTool(server="codex", toolName="codex", arguments={
"prompt": "任务描述...",
"cwd": "/absolute/path",
"topic": "review-auth_module-v1",
"sandbox": "read-only"
})
| 参数 | 必填 | 说明 |
|---|---|---|
prompt |
是 | 任务指令 |
cwd |
是 | 工作目录（绝对路径） |
topic |
是 | 任务标识，格式见下方 |
sandbox |
是 | read-only / full-access |
session_id |
否 | 恢复之前的会话（多轮对话） |
server取决于 MCP 配置（常见：codex、codexmcp）。
Topic 命名
格式：<type>-<description>-v<version>
| type | 场景 | sandbox |
|---|---|---|
review |
审阅、分析 | read-only |
implement |
功能实现、修复、重构 | full-access |
longrun |
长任务后台分派 | full-access |
test |
测试补充、测试重构 | full-access |
- description 用
_分割单词：auth_module、db_migration - version 方便标记轮次：
v1→v2
Resume 规则：topic 版本号 +1（如 v1 → v2），传入上次的 session_id。
版本号变化不会创建新 worktree——worktree 和分支名基于 <type>-<description> 生成（不含版本），自动复用。
示例：review-auth_handler-v1、implement-user_register-v1、longrun-async_refactor-v1
模式选择
默认使用阻塞模式（codex）。 仅在满足以下条件时使用 codex_dispatch：
- 用户明确要求分派/后台执行/长任务，或
- 你有清晰的计划，Codex 后台执行期间你自己有实质性工作要做
需要 Codex 的任务
│
├─ 审阅/分析 → codex (read-only)
├─ 写代码/修复 → codex (full-access)
├─ 多模块并行 → 多个 codex (full-access) 并发
└─ 长任务 + 用户要求分派 → codex_dispatch (full-access)
| 场景 | 详情 |
|---|---|
| 代码审阅 | scenarios/review.md |
| 并行实现 | scenarios/parallel.md |
| 后台分派 | scenarios/dispatch.md |
| MCP 不可用 | scenarios/cli-fallback.md |
Prompt 编写指南和完整示例已融入各场景文档中。
MCP 不可用处理
- 立即停止 — 不继续依赖 Codex 的步骤
- 告知用户 — 提供选项："等待恢复" 或 "CLI 降级"（见 cli-fallback.md）
- 严禁：自己执行 Codex 任务、编造结果、静默跳过
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.
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.
- 2d ago First seen · 123 lines · 61 tokens per session scan A d82cc5b6b8c7
codexmcp-using is a skill published in the GitHub repository shilong20/codexmcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 1,302 once invoked, about $0.0003 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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.