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/loopnpx skills add XiaomiMiMo/MiMo-Code --skill loopgit 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 | $0.00101 | $0.01566 |
| Opus 5 | $0.00051 | $0.00783 |
| Sonnet 5 | $0.00020 | $0.00313 |
| Haiku 4.5 | $0.00010 | $0.00157 |
Grade A, and why
loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/loop — schedule a recurring prompt
This skill turns a free-form [interval] <prompt> line into a cron tool call and runs the prompt once right away.
1. Parse the input
The user's text is whatever appears after /loop . Apply the three rules below in order and stop at the first match.
-
Leading interval token. If the first whitespace-separated token matches the regex
^\d+[smhd]$(case-insensitive), that token is the interval. Examples:5m,2h,1d,30s. The rest of the input is the prompt. -
Trailing
every <N><unit>clause. Otherwise, look for a clause at the end of the input of the formevery <N><unit>orevery <N> <unit-word>where<unit>iss|m|h|dand<unit-word>issecond(s)|minute(s)|hour(s)|day(s). Strip the clause; what's left is the prompt; the captured<N><unit>is the interval. Examples:every 20m,every 5 minutes,every 2 hours. -
Default. No interval found → interval is
10m, the whole input is the prompt.
If the input is empty, or is only an interval with no prompt body, reply with a one-line usage hint (/loop [interval] <prompt>) and stop. Do not schedule anything.
2. Special: empty prompt with autonomous opt-in
When the user types /loop <interval> (interval only) and the project has explicitly opted into autonomous-loop mode (a session-level flag the runtime sets), the prompt body is the sentinel <<autonomous-loop>>. The scheduler expands this sentinel at fire time into a self-directed tick instruction. If autonomous mode is not enabled, treat empty as the usage-hint case above.
3. Map interval → 5-field cron expression
| Pattern | Cron expression |
|---|---|
Ns |
treat as ceil(N/60)m; minimum is 1m |
Nm where N is 1–59 and divides cleanly (1, 2, 3, 4, 5, 6, 10, 12, 15, 20, 30) |
*/N * * * * |
Nm where N ≥ 60 and N/60 divides 24 (1, 2, 3, 4, 6, 8, 12) |
0 */(N/60) * * * |
Nh where N is 1–23 and divides 24 |
0 */N * * * |
Nd where N divides 31 sensibly (1, 2) |
0 0 */N * * |
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 · 80 lines · 101 tokens per session scan A 1d74c9a1c575
loop is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,904 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 1,566 once invoked, about $0.0005 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…