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/modern-python-toolchainnpx skills add XiaomiMiMo/MiMo-Code --skill modern-python-toolchaingit 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 | $0.00105 | $0.01476 |
| Opus 5 | $0.00053 | $0.00738 |
| Sonnet 5 | $0.00021 | $0.00295 |
| Haiku 4.5 | $0.00011 | $0.00148 |
Grade C, and why
modern-python-toolchain scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://astral.sh/uv/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modern Python Toolchain
A guide for setting up Python projects with modern, fast tooling: uv (package/project manager), ruff (linter/formatter), and pyright (type checker).
Installing uv
uv is an extremely fast Python package and project manager. It replaces pip, pip-tools, pipx, pyenv, virtualenv, poetry, etc.
# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
# Homebrew (macOS)
brew install uv
After installation, restart your shell or run source $HOME/.local/bin/env (the installer prints the exact command).
For detailed information: https://docs.astral.sh/uv/
uv basics
Python version
Pin a single Python minor version. The recommended default is 3.12 (broadest ecosystem support — PyTorch, CUDA images, downstream libraries). Python 3.14 is the latest stable; prefer it for new projects unless you depend on packages that haven't added 3.14 support yet.
# pyproject.toml
requires-python = "==3.12.*"
Install Python via uv (no system Python needed):
uv python install 3.12
Creating a new project
uv init # Create new project with pyproject.toml
uv init -p 3.12 # Specify Python version
Common commands
uv add requests # Add dependency
uv add --dev ruff "pyright[nodejs]" # Add dev dependencies
uv remove requests # Remove dependency
uv sync # Install from lockfile
uv run COMMAND # Run command in project environment
uv run script.py # Run a script
uv run python -c "..." # Run Python one-liner
uvx TOOL ARGS # Run a tool without installing it
Rules
- Never use
pipin uv projects — alwaysuv addfor packages. - Never run
python script.pydirectly — alwaysuv run script.pyto ensure the correct environment. For one-liners useuv run python -c "...". - Don't manually manage environments with
python -m venvorsource .venv/bin/activate— uv handles this automatically. uvxruns tools from PyPI by package name without installing them permanently.
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 · 203 lines · 105 tokens per session scan C 308966220356
modern-python-toolchain is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,904 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 1,476 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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…