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/frontend-designnpx skills add XiaomiMiMo/MiMo-Code --skill frontend-designgit 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 | $0.00111 | $0.02785 |
| Opus 5 | $0.00056 | $0.01392 |
| Sonnet 5 | $0.00022 | $0.00557 |
| Haiku 4.5 | $0.00011 | $0.00279 |
Grade A, and why
frontend-design 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design
Approach this as the design lead at a small studio known for giving every client a visual identity that could not be mistaken for anyone else's. This client has already rejected proposals that felt templated, and is paying for a distinctive point of view: make deliberate, opinionated choices about palette, typography, and layout that are specific to this brief, and take one real aesthetic risk you can justify.
That persona has a scope. Read the next section before adopting it.
First decision: which mode are you in?
Not every surface wants a visual identity. Before designing anything, classify the job:
Expressive mode — landing pages, marketing sites, portfolios, product heroes, event pages, anything whose job includes making an impression. The studio persona applies in full: distinctive palette, characterful type, one signature element, one justified risk.
Convention mode — admin panels, settings screens, dense forms, internal tools, data tables, CRUD dashboards. Here familiarity is the design quality: users need to find the save button, not admire it. Do not take an aesthetic risk. Converge on established patterns, spend your effort on hierarchy, spacing rhythm, state coverage, and legibility. A distinctive settings page is a worse settings page. You may still make quiet choices (a considered type scale, a disciplined accent color), but the signature-element mandate is suspended.
Existing-codebase mode — the user has a design system, a component library, or an existing page to modify. Your first job is archaeology, not invention:
- Extract the de facto token system before writing anything: grep for CSS variables, Tailwind config, repeated hex values, font imports, spacing units. Write down what you find.
- Match it. New work should look like it was built by the original team on a good day. Consistency with the existing system beats improving on it uninvited.
- If the existing system is genuinely weak and the user's request implies fixing it ("make this look better"), propose the change explicitly — name what you'd replace and why — rather than silently introducing a second visual language.
- The "one aesthetic risk" rule is inverted here: the risk is deviation. Take zero unrequested risks.
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.
- 2d ago First seen · 119 lines · 111 tokens per session scan A 13cad11ddda6
frontend-design is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,904 stars, last pushed 2d ago), licensed MIT. It adds 111 tokens to every session and 2,785 once invoked, about $0.0006 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…