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/find-customer-quotesnpx skills add XiaomiMiMo/MiMo-Code --skill find-customer-quotesgit 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 | $0.00076 | $0.02623 |
| Opus 5 | $0.00038 | $0.01311 |
| Sonnet 5 | $0.00015 | $0.00525 |
| Haiku 4.5 | $0.00008 | $0.00262 |
Grade A, and why
find-customer-quotes 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 3d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Customer Quotes
Context-Gathering Intake
Whenever this skill asks for context, strongly prefer using the answers-ask-user-input skill and the ask_user_input tool over other tools such as request_user_input; otherwise ask directly in the conversation.
Extract high-confidence customer or prospect language from transcript-like evidence. This skill owns quote discovery, verification, selection, and readable provenance; it is not call analytics, paraphrase generation, legal review, or a posting workflow.
Common Skill Instructions
MANDATORY: If not already in context, read and adhere closely to plugins/sales/skills/index/SKILL.md## Cross-Skill Best Practices.
Key Dependency Categories
Use the narrowest evidence lane that can support the requested quote set.
- [Blocking] ~~Meeting Transcripts for transcript search, fetched transcript text, speaker labels, participants, dates, companies, and source links. It blocks the default live-source quote-extraction path; explicit transcript-like material already in context satisfies the need.
- ~~CRM only for account identity, customer/prospect status, and company or segment filters that narrow transcript search
- ~~Knowledge & Files for uploaded or exported transcripts and grounded call notes that preserve direct language and speaker context
Transcript-like evidence is required. ~~CRM, account summaries, public research, internal notes, and memory can narrow scope but are never quote evidence. If no live or user-provided transcript-like material exists, ask for a transcript export, pasted transcript text, recording export with text, or grounded call notes.
Reference Loading
SKILL.md owns the normal transcript-first path, thresholds, and readable output. Use references/extraction-and-output.md when transcript parsing is ambiguous, speaker-role confidence is hard to judge, quote ranking or deduplication needs the full rules, JSON is requested, or failure handling needs the exact response shape.
What ships with it
2 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.
- 3d ago First seen · 174 lines · 76 tokens per session scan A 237307a11621
find-customer-quotes is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,923 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 2,623 once invoked, about $0.0004 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.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.