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/image-to-codenpx skills add XiaomiMiMo/MiMo-Code --skill image-to-codegit 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 | $0.00034 | $0.00666 |
| Opus 5 | $0.00017 | $0.00333 |
| Sonnet 5 | $0.00007 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
image-to-code 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image to Code
Translate a selected visual target into a high-quality frontend. Read ../index/SKILL.md, ../../references/critical-overrides.md, and the relevant saved context from ../user-context/SKILL.md before building.
Preconditions
- Require an unambiguous selected image, screenshot, mockup, generated result, or design frame. A written brief alone is not a visual target; route to ideation first when appropriate.
- Resolve which image is selected before editing. Ask when an ordinal or attachment is ambiguous.
- Use only the current task's relevant product context, tokens, components, assets, and references.
Workflow
- Inspect the source visual at useful detail and record its viewport, layout regions, hierarchy, spacing, typography, colors, borders, radii, shadows, imagery, icons, responsive behavior, and visible states.
- Inventory every required asset. Reuse supplied or repository assets when they match. Use an available image-generation tool for custom raster imagery and an appropriate existing icon set for UI icons. Do not substitute emoji, generic placeholders, or improvised CSS drawings for meaningful visual assets.
- Inspect the target repository and use its existing framework, package manager, component system, design tokens, and conventions. React is not required. Do not replace an established stack merely to match this workflow.
- If no target app exists, create the smallest runnable frontend supported by the harness and suited to the request; plain HTML/CSS/JavaScript is acceptable.
- Implement the full visible structure and the primary user journey. Unless requested otherwise, make navigation, tabs, menus, forms, toggles, selections, and main calls to action behave realistically without inventing backend systems.
- Match desktop or mobile based on the source. When the source is a phone UI and no device is named, verify around 390 × 844 as well as any relevant responsive behavior.
- Run the real app using its normal development or preview command.
- Capture the implementation using the browser tool selected by
../index/SKILL.mdand run../design-qa/SKILL.mdagainst the source visual. - Fix all blocking and high-impact mismatches. Save
design-qa.mdin the project root and hand off only when it recordsfinal result: passed, or clearly report a genuine capture/verification blocker.
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 · 40 lines · 34 tokens per session scan A b887ae459ff4
image-to-code is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,904 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 666 once invoked, about $0.0002 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…