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/renmengwen/musedock/agents-mdgit clone --depth 1 https://github.com/renmengwen/MuseDockWrote 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/renmengwen/musedock/agents-md)<a href="https://agentmods.dev/instructions/renmengwen/musedock/agents-md"><img src="https://agentmods.dev/badge/instructions/renmengwen/musedock/agents-md.svg" alt="Measured on agentmods" 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 | $0.01354 | $0.01354 |
| Opus 5 | $0.00677 | $0.00677 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
MuseDock 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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目协作规则
分支与工作区约束
- 日常开发默认基于
dev分支进行,包括代码修改、文档修改、依赖调整、配置变更、格式化和提交。 - 可以在
dev或从dev派生的功能分支上开发;禁止直接在main上承接日常开发。 - 在修改任何文件前,必须先确认当前 Git 分支。
- 在修改任何文件前,应检查
git status --short,识别已有未提交改动。 - 不得回滚、覆盖、格式化或顺手修改与当前任务无关的用户改动。
- 如果当前分支是
main,且任务不是发布、同步或将dev合并到main,必须立即停止工作,不得编辑文件、生成文件、格式化、提交或推送,并提醒用户先切换到dev分支。 main分支只用于稳定版本、发布、同步远端状态或从dev合并,不直接承接日常开发。- 当用户明确要求将
dev合并到main,可以切换到main执行合并和推送;合并完成后应切回dev继续开发。 - 如果用户要求在
main上直接修改业务代码或文档,需要先复述风险并等待用户再次确认。
修改范围与验证
- 修改(Edit/Update/覆盖 Write)任何已存在的文件前,必须先读取(Read)该文件的当前内容再改:工具层会直接拒绝未读先改的操作,且先读才能确认已有未提交改动与最新状态。
- 每次修改应聚焦当前任务,避免无关重构、目录重排、批量格式化或大面积样式迁移。
- 完成代码修改后,应根据改动范围运行最小必要验证,例如前端构建、类型检查、相关单测或手动启动验证。
- 如果验证无法运行,必须在结果说明中写明原因和剩余风险。
用户可见文案
- 默认所有展示给用户看的文案必须使用中文,包括按钮、提示、弹窗、状态、错误信息、空状态、加载文案和操作结果。
- 技术专有名词、接口字段、品牌名、文件名、命令、环境变量、第三方服务名可以保留英文,例如
OpenAI API、ffmpeg、OPENAI_API_KEY。 - 如果必须展示后端或第三方返回的英文错误,应尽量补充中文解释,避免只把英文原样抛给用户。
前端 UI 与样式
- 新增或重构面向用户的前端 UI 时,默认优先使用 Tailwind CSS utility class 与官方
shadcn/ui组件体系。 shadcn/ui接入默认参考 Vite 安装文档:https://www.shadcn-ui.cn/docs/installation/vite 。- 通用控件应优先复用项目已有
shadcn/ui组件;确需新增时,使用项目当前依赖和配置通过 CLI/registry 引入或同步官方组件,避免无关升级。 - 按钮、输入框、下拉框、弹窗、标签页、徽标、提示、表格、Tooltip、Checkbox、Switch 等通用控件,应优先来自官方
shadcn/ui组件;如果确需改造,优先在引入的组件基础上做项目化调整,并保留清晰来源和 API 边界。 - 避免继续向
frontend-react/src/styles.css追加大段跨页面全局样式;确需新增 CSS 时,应优先限制在小范围组件、复杂布局、媒体编辑器、第三方渲染容器或 Tailwind 难以清晰表达的场景,并保持选择器边界清楚。 - 重构历史页面时采用渐进迁移,不要求一次性把已有手写 CSS 全量改为 Tailwind;每次迁移应同步清理已不再使用的旧样式。
- 复杂工具界面(例如视频编辑器)可以阶段性保留局部 CSS,但新增通用操作控件和状态展示仍应优先走官方
shadcn/ui组件。
接口加载状态
- 所有会触发接口请求的用户操作,必须在请求期间展示明确的 loading 提示。
- loading 提示应说明正在执行的动作,例如“正在加载评论和二级评论...”“正在准备素材...”“正在请求音频转写...”。
- 请求完成后必须更新为成功、失败、未配置、需登录、需验证等明确状态,不能让 loading 状态悬停。
- 新增接口调用时,需要同时检查对应按钮禁用态或重复点击保护,避免用户连续触发同一请求。
- 新增或修改接口调用时,应尽量区分网络失败、未登录、权限不足、配置缺失、第三方限流和未知错误,并给出中文可操作提示。
依赖与敏感信息
- 不得为少量逻辑轻易新增依赖;新增依赖前应优先检查标准库、浏览器原生能力、现有依赖和项目已有工具。
- 确需新增依赖时,应说明用途,并同步更新对应锁文件。
- 不得提交真实账号、Cookie、Token、API Key、代理密码或其他敏感信息。
- 示例配置只能使用占位值;本地密钥应优先通过
.env、本地配置文件或运行环境读取。
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.
- 5d ago First seen · 62 lines · 1,354 tokens per session scan A ea31dcee7c46
MuseDock AGENTS.md is an instructions file published in the GitHub repository renmengwen/MuseDock (101 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,354 tokens to every session, about $0.0068 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
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.
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
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).