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/product-designnpx skills add XiaomiMiMo/MiMo-Code --skill product-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 | $0.00057 | $0.00538 |
| Opus 5 | $0.00028 | $0.00269 |
| Sonnet 5 | $0.00011 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
product-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 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Design
This is the single entry point for a code-agent-oriented Product Design bundle. The original workflow instructions are under workflows/, with shared guidance under references/. The bundled React/Vite prototype template and package metadata are intentionally excluded.
Route the request
- Read
workflows/index/SKILL.mdcompletely. Treat it as the authoritative plugin-level scope, routing, sequencing, and browser-choice policy. - Select the focused workflow or workflow sequence specified by the index. Read every selected workflow's
SKILL.mdcompletely before acting. - Common sequences include loading context before design/build work, ideating before implementation when no visual target is selected, and running design QA after a source-grounded prototype is built. Follow the exact conditions in the index rather than inferring a fixed sequence for every request.
- Resolve relative links from the file that contains the link. Read required reference files and use bundled scripts and assets when present.
- Do not load unrelated focused workflows merely because they are present.
Bundled capabilities
Focused workflows live in workflows/: user-context, get-context, research, audit, ideate, url-to-code, image-to-code, design-qa, and share.
Shared reusable guidance lives in references/. Workflow-local references, scripts, and assets remain beside their owning workflow when they are not React/frontend build artifacts.
Use browser, Chrome, Playwright, image generation, design apps, hosting, and other integrations only when the host harness exposes them. The bundle's mention of a tool does not prove availability or authorization. Follow host permissions and the selected workflow's fallback behavior.
When creating a prototype, prefer the target repository's existing frontend stack. If there is no existing app and the user still wants a runnable web prototype, create the smallest suitable implementation using host-supported tools; React is not required. Do not look for the removed bundled prototype template or bootstrap script.
What ships with it
27 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.
- references/communication-protocol.md 1.9 KB
- references/critical-overrides.md 4.6 KB
- references/existing-codebase-edits.md 945 B
- workflows/audit/agents/openai.yaml 261 B
- workflows/audit/references/design-audit-framework.md 2.0 KB
- workflows/audit/SKILL.md 8.3 KB
- workflows/design-qa/agents/openai.yaml 231 B
- workflows/design-qa/references/qa-rubric.md 5.1 KB
- workflows/design-qa/SKILL.md 9.7 KB
- workflows/get-context/agents/openai.yaml 220 B
- workflows/get-context/SKILL.md 2.8 KB
- workflows/ideate/agents/openai.yaml 221 B
- workflows/ideate/SKILL.md 12 KB
- workflows/image-to-code/agents/openai.yaml 281 B
- workflows/image-to-code/SKILL.md 3.3 KB
- workflows/index/agents/openai.yaml 290 B
- workflows/index/SKILL.md 9.7 KB
- workflows/share/agents/openai.yaml 205 B
- workflows/share/SKILL.md 1.7 KB
- workflows/url-to-code/agents/openai.yaml 236 B
- workflows/url-to-code/SKILL.md 2.6 KB
- workflows/user-context/agents/openai.yaml 293 B
- workflows/user-context/plugin-author-config/user-context-template.md 1.5 KB
- workflows/user-context/references/onboarding.md 2.2 KB
- workflows/user-context/scripts/init_user_context.py 2.5 KB runs code
- workflows/user-context/scripts/user_context_preflight.py 6.0 KB runs code
- workflows/user-context/SKILL.md 5.9 KB
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 · 34 lines · 57 tokens per session scan A e2cd44643418
product-design is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,904 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 538 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 2026-08-30.
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…