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/memory-searchnpx skills add XiaomiMiMo/MiMo-Code --skill memory-searchgit 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 | $0.00078 | $0.01953 |
| Opus 5 | $0.00039 | $0.00977 |
| Sonnet 5 | $0.00016 | $0.00391 |
| Haiku 4.5 | $0.00008 | $0.00195 |
Grade A, and why
memory-search 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Search: SQLite Trajectory Database
Direct SQL access to mimocode's trajectory database for structured analysis that the memory (BM25 over curated markdown) and history (FTS over raw messages) tools cannot perform — aggregation, filtering by tool/status/time, cross-session pattern detection, and execution chain inspection.
When to use
- You need to aggregate or count across sessions (e.g. "which tool fails most often?", "how many sessions touched file X?").
- You need to filter by structure — tool name, status, agent_id, time range — not just text content.
- You need to view a complete execution chain for a session (every tool call in order).
- You need to verify a memory claim against what actually happened (the DB is the source of truth).
- The
memoryandhistorytools returned nothing useful despite multiple query attempts.
Locating the database
# Typically at this path. MIMOCODE_DB env var overrides if set.
sqlite3 -readonly ~/.local/share/mimocode/mimocode.db ".tables"
Always use -readonly or only SELECT queries — never modify the database.
Schema
| Table | Purpose | Key columns |
|---|---|---|
session |
Session metadata | id, project_id, title, time_created, parent_id |
message |
User/assistant turns | id, session_id, agent_id, time_created, data (JSON: $.role) |
part |
Message parts (text, tool calls, steps) | id, message_id, session_id, time_created, data (JSON) |
task |
Task tree | id, session_id, summary, status |
task_event |
Task state transitions | id, session_id, task_id, at, kind, summary |
actor_registry |
Subagent/peer history | session_id, actor_id, agent, mode, status, description |
Part types in part.data
{"type":"text","text":"..."}— agent text output{"type":"tool","tool":"<name>","callID":"...","state":{"status":"completed","input":{...},"output":"..."}}— completed tool call{"type":"tool","tool":"<name>","callID":"...","state":{"status":"error","input":{...},"error":"..."}}— failed tool call (nooutputfield; error message in$.state.error){"type":"step-start"}/{"type":"step-finish","tokens":...}— step boundaries{"type":"compaction","auto":true/false}— compaction boundary{"type":"checkpoint",...}— checkpoint/rebuild boundary
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 · 166 lines · 78 tokens per session scan A b0a34e7878f7
memory-search is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,904 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 1,953 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.
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…