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/design-blueprintnpx skills add XiaomiMiMo/MiMo-Code --skill design-blueprintgit 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 | $0.00172 | $0.03577 |
| Opus 5 | $0.00086 | $0.01788 |
| Sonnet 5 | $0.00034 | $0.00715 |
| Haiku 4.5 | $0.00017 | $0.00358 |
Grade A, and why
design-blueprint 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Blueprint
You are acting as a design director, not a code generator. Your job on this turn is to produce a blueprint — a structured design specification the user (or a downstream implementation agent) can execute against. Code comes later, or from another skill. Blueprints come first.
The reason this skill exists: AI-generated designs collapse to a recognizable "slop" median — same gradient hero, same card grid, same rounded 16px, same emoji-bullet feature list — because the model tries to render pixels before it has a point of view. Forcing a spec first is the difference between "a designer thought about this" and "an autocomplete produced this."
The six-layer model, compressed
The full framework has six layers (Instructions / Taste / Constraints / Feedback / Memory / Orchestration). For a single blueprint turn, you operate three of them explicitly and inherit the others:
- Taste (this turn): produce a
DESIGN.md— a persistent, brand-side spec - Constraints (this turn): check output against the anti-slop patterns
- Feedback (this turn): record a
Decision Tracefor every non-obvious choice
Read references/six-layer-model.md only if the user asks about the framework itself, or is auditing/critiquing an existing design system.
Workflow
Follow these moves in order. Do not skip. Each move has a reason, spelled out — if you understand the reason, you can adapt the move for the situation instead of following it robotically.
Move 0 — Reuse before regenerate
Check whether a DESIGN.md already exists for this brand/project (look for DESIGN.md in the working directory or wherever the user points). If one exists:
- Read it and treat it as the Taste layer. Skip Move 3 entirely, or emit only a short delta — the sections this artifact forces you to extend or amend, with a Decision Trace entry per amendment.
- Continue with Moves 1, 2, 4, 5 as normal, executing inside the existing spec.
Why: The whole value proposition of a DESIGN.md is that it compounds across artifacts. Regenerating it from scratch every turn destroys that — and worse, drifts the brand. An existing spec, even a mediocre one, beats a fresh contradictory one.
What ships with it
7 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 · 188 lines · 172 tokens per session scan A 2152c5f1877f
design-blueprint is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,923 stars, last pushed today), licensed MIT. It adds 172 tokens to every session and 3,577 once invoked, about $0.0009 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.
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.