MuseDock: Instructions file for Codex

AGENTS.md

MuseDock AGENTS.md is an instructions file for Codex, OpenCode from renmengwen/MuseDock. It costs 1,459 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for MuseDock covering collaboration rules, branch use, change boundaries, verification, Chinese user-facing text, and interface styling.

In plain words
What is it for?
Use them to check Git state before edits, follow the project’s branch policy, make focused changes, run suitable checks, and build user interfaces with the project’s preferred tools.
Why use it?
They reduce the risk of editing the wrong branch, overwriting existing work, changing unrelated files, or showing inconsistent language in the interface.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is renmengwen/MuseDock's own configuration. It tells Codex and OpenCode how to work on MuseDock itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MuseDock configures →

Reuse

Borrowing it

Nothing to install: this file belongs to renmengwen/MuseDock. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/renmengwen/MuseDock/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/renmengwen/MuseDock

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for MuseDock AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/renmengwen/musedock/agents-md/github.svg)](https://agentmods.dev/instructions/renmengwen/musedock/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/renmengwen/musedock/agents-md"><img src="https://agentmods.dev/badge/instructions/renmengwen/musedock/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.

agentmods 80×15 button for MuseDock AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/renmengwen/musedock/agents-md"><img src="https://agentmods.dev/badge/instructions/renmengwen/musedock/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,459 This file is loaded in full into every session.
When invoked 1,459 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01459 $0.01459
Opus 5.5 $0.00584 $0.00584
Sonnet 5.5 $0.00292 $0.00292
Haiku 4.5 $0.00146 $0.00146

Measured 1mo ago against content hash 54953f61e6d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

AGENTS.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 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。
  • 新增或修改功能时,同步更新项目 README.md;只写用户理解和使用所必需的信息,优先修订已有内容,省略实现细节、开发过程和重复说明。现有说明仍准确且足够时,可不改。
  • 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。
  • 禁止运行全量测试;只允许运行与本次改动相关的测试(例如指定的测试文件、测试目录或匹配用例),除非用户明确要求执行全量测试。
  • 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。

Read the full file on GitHub · 64 lines

Changes

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.

  1. 1mo ago Changed · +1 lines · +59 tokens per session 54953f61e6d8
  2. 1mo ago Changed · +1 lines · +46 tokens per session 6b69ce90dd80
  3. 2mo ago First seen · 62 lines · 1,354 tokens per session scan A ea31dcee7c46

Subscribe to this mod's changes

MuseDock AGENTS.md is an instructions file published in the GitHub repository renmengwen/MuseDock (169 stars, last pushed 18d ago), licensed Apache-2.0. It adds 1,459 tokens to every session, about $0.0058 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.

Related

MuseDock AGENTS.md compared with instructions from other repositories

MuseDock AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
MuseDock AGENTS.mdrenmengwen/MuseDockInstructions file16918d agoApache-2.0A1,459Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode