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 instructions/xiaomimimo/mimo-code/agents-mdgit 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 | $0.01169 | $0.01169 |
| Opus 5 | $0.00584 | $0.00584 |
| Sonnet 5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
MiMo-Code AGENTS.md 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MiMo-Code
Conventions
- Use MiMoCode Compose skills when available, otherwise use superpowers skill if installed.
- To regenerate the JavaScript SDK, run
./packages/sdk/js/script/build.ts. - ALWAYS USE PARALLEL TOOLS WHEN APPLICABLE.
- The default branch in this repo is
main. - CI triggers on
main. - Prefer automation: execute requested actions without confirmation unless blocked by missing info or safety/irreversibility.
- Install deps with
bun ci(=bun install --frozen-lockfile) — install perbun.lock, don't mutate the lockfile. ⛔ Do NOT usebun install/npm install.
Core Focus
Development focuses on the TUI (packages/opencode/src/cli/cmd/tui/) and the engine core it runs on. The Web, App and Desktop surfaces are not currently maintained. In practice this means an operation should default to checking the TUI path first.
Style Guide
General Principles
- Keep things in one function unless composable or reusable
- Avoid
try/catchwhere possible - Avoid using the
anytype - Use Bun APIs where the runtime is Bun-only, like
Bun.file()in the TUI (src/cli/cmd/tui/); build-time macros are fine anywhere, as they never reach the shipped runtime - In core code reachable from
src/node.ts, prefer the Node equivalent when one exists —createHashoverBun.CryptoHasher,prepare()over bun:sqlite'squery()— as that code also ships throughscript/build-node.tsand must run on plain Node - Bun-only calls in core escape both
typecheckandbun test, which run on Bun; existing usage needs no urgent removal, and APIs with no Node equivalent may stay until a runtime seam exists - Rely on type inference when possible; avoid explicit type annotations or interfaces unless necessary for exports or clarity
- Prefer functional array methods (flatMap, filter, map) over for loops; use type guards on filter to maintain type inference downstream
- In
src/config, follow the existing self-export pattern at the top of the file (for exampleexport * as ConfigAgent from "./agent") when adding a new config module.
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 · 139 lines · 1,169 tokens per session scan A bbf57c5276e3
MiMo-Code AGENTS.md is an instructions file published in the GitHub repository XiaomiMiMo/MiMo-Code (12,904 stars, last pushed 2d ago), licensed MIT. It adds 1,169 tokens to every session, about $0.0058 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 instructions, from other repositories
muxlayer AGENTS.md
Instructions for dengmengmian/muxlayer, covering 核心原则, 工程规范, 输出规范, tdd 模式 and 边界.
deepseek-vision-skill CLAUDE.md
Claude Code instructions for reF0o0/deepseek-vision-skill, covering claude.md, 项目概述, 目录结构, 常用命令 and 架构要点.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).