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 skills add Lingtai-AI/lingtai --skill xiaomi-mimogit clone --depth 1 https://github.com/Lingtai-AI/lingtaiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lingtai-ai/lingtai/xiaomi-mimo)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/xiaomi-mimo"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/xiaomi-mimo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/xiaomi-mimo"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/xiaomi-mimo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 94 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
What 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 5.1 | $0.00342 | $0.02508 |
| Opus 5 | $0.00171 | $0.01254 |
| Sonnet 5 | $0.00068 | $0.00502 |
| Haiku 4.5 | $0.00034 | $0.00251 |
Grade A, and why
xiaomi-mimo scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **Full doc dump** (one curl → every public doc page concatenated) | [`platform.xiaomimimo.com/llms-full.txt`](https://platform.xiaomimimo.com/llms-full.txt) | How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xiaomi-mimo
This is a discovery protocol, not a reference. It teaches you where to look for current MiMo capabilities — it does not mirror them. Anything API-shaped (model IDs, request schemas, voice catalogues, quotas) drifts faster than this manual; fetch the live docs every time.
Where to look
Two URLs and an LLM-friendly bulk dump are all the agent needs to bootstrap full knowledge of the API:
| Purpose | URL |
|---|---|
| Doc index (start here for any specific question) | platform.xiaomimimo.com/llms.txt |
| Full doc dump (one curl → every public doc page concatenated) | platform.xiaomimimo.com/llms-full.txt |
| Marketing / model gallery (skim once for the vibe) | mimo.xiaomi.com |
# Quick orientation — what doc pages exist right now?
curl -s https://platform.xiaomimimo.com/llms.txt | head -60
# Full dump — when you need everything in context (much larger)
curl -s https://platform.xiaomimimo.com/llms-full.txt | wc -l
The doc index is structured so you can grep for what you need (e.g. grep -i tts, grep -i pricing, grep -i multimodal). Each entry has a verbatim URL — fetch the specific page once you've located it.
Roughly what's behind a MiMo API key
Enough context for the agent to know what kind of question to ask the docs. Verify model IDs and capability claims against the live docs every time — Xiaomi rotates suffixes and adds new variants regularly.
Three rough families share one https://<host>/v1/chat/completions endpoint:
- Text-only chat models — long-context reasoning and tool use. Use for plain LLM work; one is the 1M-context flagship.
- Multimodal-input chat models — accept image, audio, AND video as content parts (
type: "image_url" | "input_audio" | "video_url") alongside text. Output is text. Use for transcription, image OCR, scene description, audio-visual joint reasoning, etc. - Text-to-speech models — accept text, return base64-encoded audio. Three flavours: a built-in voice catalogue, a voice-design variant where you describe the voice in natural language, and a voice-clone variant where you upload a reference audio sample.
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.
- 9d ago First seen · 155 lines · 342 tokens per session scan A 1934bd14cae2
xiaomi-mimo is a skill published in the GitHub repository Lingtai-AI/lingtai (677 stars, last pushed yesterday), licensed Apache-2.0. It adds 342 tokens to every session and 2,508 once invoked, about $0.0017 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.