Borrowing it
Nothing to install: this file belongs to NERDSORG/Mutsumi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NERDSORG/Mutsumi/main/AGENTS.mdgit clone --depth 1 https://github.com/NERDSORG/MutsumiWrote 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/instructions/nerdsorg/mutsumi/agents-md)<a href="https://agentmods.dev/instructions/nerdsorg/mutsumi/agents-md"><img src="https://agentmods.dev/badge/instructions/nerdsorg/mutsumi/agents-md/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/instructions/nerdsorg/mutsumi/agents-md"><img src="https://agentmods.dev/badge/instructions/nerdsorg/mutsumi/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01385 | $0.01385 |
| Opus 5.5 | $0.00554 | $0.00554 |
| Sonnet 5.5 | $0.00277 | $0.00277 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
Mutsumi 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 19d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mutsumi 开发约定(Agent 贡献者版)
Mutsumi 是一个 VS Code 多 Agent 对话环境:Agent 会话以 .mtm 文件持久化,经 Custom Editor + WebView 呈现。本文档写给参与本项目开发的 AI Agent,含有最重要的架构约束与工程约定;各模块内部的机制细节以模块 docstring 为准。
架构:三层拆分
后端 (src/backend, src/agent) → 前端适配器 (src/frontend) → 前端 UI (如 frontends/webview/ui)
- 后端是唯一状态权威,零 UI 依赖:不得 import
vscode.window/ WebView 类型,只用workspace.fs、Uri、EventEmitter等纯数据面 API。需要用户可见的通知时,广播session.error。 - 后端 ↔ 前端适配器:唯一通道是
EventBus的类型化事件协议。前端到后端只有 FtB(意图),后端到前端只有 BtF(事实);前端永不监听 FtB;任何改变后端状态的 FtB 必须广播对应 BtF。除sessions.changed、settings.autoApprove外,事件都携带sessionId路由。 - 事件协议自含于
src/backend/events.ts:payload 映射与事件名数组互相satisfies校验,registerBackendHandlers的 mapped type 强制穷尽——新增事件漏登任何一处,编译直接报错。 - 适配器 ↔ 前端 UI:协议由各适配器自定,不进总线(WebView 用 adapter-local RPC 信封;将来可能有 ACP)。
- 纯前端↔适配器事务在适配器处终结:不触碰后端状态、不需要后端知情的请求(如
@补全的搜索 RPC、图片上传解析),用适配器本地机制实现,不要为它新增总线事件;把后端拉进纯前端-适配器事务是制造耦合。 - 会话的真相:
.mtm文件,sessionStore是唯一写口;运行中以内存为准,外部改文件不触发重载。
目录与文件约定
- 每个模块(含子模块)尽量独占一个目录。
- 各模块目录内:实际类型和常量集中放
types.ts;抽象接口放interfaces.ts;可复用的(尤其是无副作用的)工具函数放utils.ts。 - WebView
ui/下的代码只能 import 纯类型/纯工具,不得 import 宿主模块;静态文案由宿主t()翻译后注入(键表为WEBVIEW_LABEL_KEYS,新增文案须同步两个 l10n bundle)。
工程原则
- 最小实现:不产生耦合,不产生冗余。优先考虑能否用一条或少数几条正交的声明式规则"涌现"出复杂行为,而不是堆叠命令式逻辑。
- 最小抽象:不写只有一个消费者的抽象,除非路线图上有确定的其他消费者。
- 发现耦合或冗余就重构:既有代码已耦合/冗余,或原设计在加新功能时必然退化为耦合/冗余,就重构。重构时不要追求最小变更——如果某个功能成了架构精简的拦路虎,可以直接砍掉。
- 不需要重构时反过来,追求最小变更:例如实现 UI 行为时先考虑纯 CSS,CSS 做不到再上 JS。
注释与命名
- 注释即纯技术文档:只描述当前代码的架构设计与功能行为。禁止教学性内容;禁止只有看过特定对话才能理解的表述(如引用设计文档的章节编号、对话中的选项字母或编号);禁止叙述历史版本的错误行为或"为什么不要那样做"。
- 例外:如果某个错误做法极其符合直觉、按直觉写必被坑,可以加防呆警示(指向坑本身,不指向历史)。
- 标识符(变量/类/属性/函数/模块)按正式工程标准命名,不带对话或教学色彩。
- 事实上,本项目中的 JSDoc 注释就是本项目的技术文档。通过及时维护所有 JSDoc 注释,可以尽可能轻松地为人类读者和将来的 Agents 读者提供清晰准确的方法/类/模块语义。这就是为什么我们必须要确保它描述,且仅描述,当前代码的行为,并随代码改动而改动。
构建与验证
包管理器是 pnpm(新环境先 corepack enable;不要回退 npm)。提交前必须通过:
pnpm run check-types # tsc --noEmit(主配置 + webview 的 tsconfig.renderer.json)
node esbuild.js # 打包
git diff --check # 空白符检查
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.
- 19d ago Changed · -168 lines · -4,538 tokens per session c80ca6eaa7f9
- 25d ago Changed · +1 lines · +308 tokens per session e5e0cddd1f9b
- 26d ago Changed · +36 tokens per session 60db195db103
- 1mo ago Changed · -114 lines · -143 tokens per session 6b6e87839a44
- 1mo ago Changed · +3 lines · +283 tokens per session ef289e6affd1
- 1mo ago Changed · -24 tokens per session 6cdb2b227611
- 2mo ago First seen · 333 lines · 5,463 tokens per session scan A 151fb79b9e8b
Mutsumi AGENTS.md is an instructions file published in the GitHub repository NERDSORG/Mutsumi (20 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,385 tokens to every session, about $0.0055 per session on Opus 5.5. 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.
Mutsumi AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Mutsumi AGENTS.mdNERDSORG/Mutsumi | Instructions file | 20 | 5d ago | Apache-2.0 | A | 1,385 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |