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/xiaomimimo/mimo-code/codexnpx skills add XiaomiMiMo/MiMo-Code --skill codexgit clone --depth 1 https://github.com/XiaomiMiMo/MiMo-CodeWhat 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 | $0.00108 | $0.02367 |
| Opus 5 | $0.00054 | $0.01184 |
| Sonnet 5 | $0.00022 | $0.00473 |
| Haiku 4.5 | $0.00011 | $0.00237 |
Grade A, and why
codex 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 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.
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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex CLI
Use Codex CLI as a deterministic, non-interactive worker suitable for automation and agent orchestration.
Operating Rules
- Use
codex exec, not the interactivecodexTUI. - Pass the task as the positional
PROMPTargument. Do not use-pfor the prompt;-pselects a profile. - For ordinary unattended code changes, prefer:
codex exec \
-C /path/to/repo \
--sandbox workspace-write \
--ask-for-approval never \
"<TASK>"
- Use
--yoloonly inside an externally hardened and disposable runner. It disables Codex approvals and sandboxing. - For harnesses and CI, prefer
--jsonplus--output-last-message. - Do not make the run depend on a human answering questions. Resolve ambiguity using repository evidence and conservative defaults.
- Treat credentials as secrets. Inject
CODEX_API_KEYonly into the singlecodex execprocess when possible. - Before giving version-sensitive advice, inspect
codex exec --helpor current official Codex documentation if available. - On Windows, choose one execution environment per task: native PowerShell for Windows toolchains or WSL2 for Linux toolchains. Do not casually mix paths, installations, or authentication across them.
Choose the Execution Mode
Read-only analysis
Use when the task must not modify files:
codex exec \
-C /path/to/repo \
--sandbox read-only \
--ask-for-approval never \
"Analyze the repository and report risks. Do not modify files."
Workspace-scoped implementation
Use as the default for autonomous repository work:
codex exec \
-C /path/to/repo \
--sandbox workspace-write \
--ask-for-approval never \
"Implement the task, run relevant tests, and report unresolved blockers."
Externally isolated unrestricted execution
Use only when the enclosing container, VM, or sandbox enforces the real security boundary:
codex exec \
-C /workspace/repo \
--yolo \
"Implement the task and validate the result."
What ships with it
3 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.
- yesterday First seen · 302 lines · 108 tokens per session scan A ccf6930ea4f1
codex is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,904 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 2,367 once invoked, about $0.0005 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
xiaomi-tts
Use this skill when the user wants to convert text to speech using Xiaomi MiMo's TTS models (mimo-v2.5-tts). Uses OpenAI-compatible chat/completions API with audio response. Supports multiple preset voices and custom voice design. Use when 用户提到 语音合成、文字转语音、TTS、朗读、读出来、生成语音、 生成音频、文本转音频、配音、念出来、小米语音、MiMo 语音、小米 TTS。.
byok-custom-model
Register a custom LLM endpoint with your own API key for chat in Starchild. Use when adding a personal Anthropic, OpenAI, Grok, Qwen, DeepSeek, Meta (Muse Spark), NEAR AI, or Venice key as a chat model (e.g. add my Claude key, register DeepSeek, use Muse Spark 1.1).
deepseek-vision
MUST use when the user sends or asks about images, photos, screenshots, pictures, audio, video, or mixed media documents, including requests to OCR/read text from an image. Route all media through Xiaomi MiMo V2.5 (mimo-v2.5) and mimo-v2.5-asr via scripts/mimo.py; never use local OCR, viewimage, native vision…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…