Borrowing it
Nothing to install: this file belongs to chuancyzhang/deepseek-cowork. 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/chuancyzhang/deepseek-cowork/main/AGENTS.mdgit clone --depth 1 https://github.com/chuancyzhang/deepseek-coworkWrote 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/chuancyzhang/deepseek-cowork/agents-md)<a href="https://agentmods.dev/instructions/chuancyzhang/deepseek-cowork/agents-md"><img src="https://agentmods.dev/badge/instructions/chuancyzhang/deepseek-cowork/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/chuancyzhang/deepseek-cowork/agents-md"><img src="https://agentmods.dev/badge/instructions/chuancyzhang/deepseek-cowork/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 | $0.02378 | $0.02378 |
| Opus 5.5 | $0.00951 | $0.00951 |
| Sonnet 5.5 | $0.00476 | $0.00476 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade A, and why
deepseek-cowork 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 3d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
本地 Agent 说明
沟通
- 面向用户的叙述默认使用简体中文;代码、命令和技术标识保持英文。
- 先给影响与结论,再给行动、待决策和必要证据;没有对应内容就省略。
- 技术细节只保留对理解结论、判断风险或复现结果有帮助的部分。
- 明确区分已验证事实、推测和未解决问题。
- 用户建议不适合目标时,直接说明原因并提出更合适的方案,不迎合。
- 从全局角度考虑问题,新的方案要考虑竞争情况,尽可能简洁。
执行方式
- 根据用户目标和已授权范围持续完成工作。用户要求“先分析”“先展示方案”时,仅完成该阶段,不修改文件或执行后续操作。
- 已授权范围内的常规实现、修复和验证自主推进;已有明确授权的事项不重复确认。
- 缺失信息会实质改变结果时,提出具体问题;等待期间继续不依赖该答案的工作。常规实现细节结合项目现状合理决定。
- 用户在任务中补充要求时,结合原目标处理;除非用户明确取消或替换任务,否则回答插入问题后继续推进。
- 遵守上层指令和权限边界。用户明确要求优先于本文件的默认约定和技能指南。
- 文件或技能规则导致暂停时,指出具体文件、条款及适用原因,区分明确要求与自行推断。
- 不要因为假想风险,主动加警告、免责声明、审批流程或安全/合规清单。
- 复杂产品、架构和调试任务先明确用户目标、约束、关键不变量与验收标准,再确定实现路径;对外简述结论和必要取舍。
项目上下文与改动范围
- 开始修改前,阅读相关代码、项目说明及适用的目录级规则,理解现有实现和工作区变更。
- 优先复用现有架构、组件与工具;改动应直接服务于当前目标,避免无关重构。
- 保留用户已有修改,不覆盖或撤销来源不明的变更。发生直接冲突时,说明冲突并确认处理方式。
- 开发、启动、测试和构建命令以仓库现有文档、脚本与 CI 配置为准,不臆造命令。
- 不擅自提交、推送或发布;用户已明确授权的操作按授权范围执行。
Prompt Prefix 与缓存
- 涉及模型请求构造、系统提示词、开发者指令、工具定义及顺序、历史消息组织或相关请求配置时,必须评估 prompt prefix 与缓存影响。
- 不涉及上述内容的改动可直接判定无影响,无需单独展开说明。
- 区分本文件对开发助手上下文的影响,与应用运行时发送给模型的 prompt prefix 影响。
- 优先保持稳定前缀;不得为缓存命中率牺牲正确性、消息可靠性和会话隔离。
- 确需改变前缀时,实施前说明具体变更与潜在影响,并取得用户确认;同一方案已获确认后不重复询问。
对话改动前置要求
- 涉及消息发送与保存、历史消息、上下文组织、流式输出、运行控制、失败恢复或会话隔离时,必须先完整阅读
local_development_notes/CONVERSATION_FIRST_PRINCIPLES.md。 - 同一任务中已完整阅读且文档未变化时,无需重复读取。
- 仅调整展示样式且不影响上述行为时,按 UI / UX 规范处理。
- 对话相关设计与实现必须以“消息可靠、过程连续、会话隔离、失败可恢复、用户可控制”为最高层判断标准。
失败处理与诊断
- 修复根本原因,不添加掩盖失败、伪造成功或未经设计替换执行路径的回退与静默降级逻辑。
- 按既定产品规则实施的重试、回滚和用户主动恢复不属于静默降级;必须保持状态可见、次数或范围有界,且不产生重复消息或重复操作。
- 失败时保留用户输入和已完成成果,提供可理解的原因与恢复路径;尚未查明根因时,明确说明已知事实。
- 新功能及关键流程变更应检查并补齐相关诊断日志,覆盖受影响的提交、启动、运行、完成和错误路径。
- 日志应支持定位任务、阶段与失败原因,避免记录密钥及不必要的敏感内容。
UI / UX 原则
从用户任务出发
- 设计前先明确:用户是谁、当前要完成什么、已有多少背景知识,以及完成任务最大的阻碍是什么。
- 按用户完成任务的顺序组织界面,不按代码模块、内部架构或配置结构组织。
- 优先复用用户熟悉的交互方式;新增概念、步骤和选项必须有明确价值。
- 发生设计取舍时,优先考虑用户能否理解、完成任务并从错误中恢复。
让用户知道如何行动
- 用户进入页面后,应能快速理解这里能做什么、当前是什么状态、下一步如何操作。
- 突出当前任务最重要的操作,减少无关信息与不必要的选择;同一任务区域最多一个视觉主操作。
- 使用用户熟悉的简洁中文。必要时保留协议与技术专名,避免直接使用内部变量名和实现术语。
- 常用操作直接可达,低频选项按需展开;影响当前决策的状态、错误原因和恢复入口直接可见。
- 技术详情应便于阅读、选择和复制;原始参数、代码、日志与结果放在明确的详情视图中。
让操作结果清楚、可靠
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.
- 3d ago Changed · -2 lines · -54 tokens per session 26e59aafafdc
- 11d ago Changed · +1 lines · +21 tokens per session 1d84c4ad97e5
- 1mo ago Changed · +73 lines · +1,054 tokens per session 78fbd3d183c0
- 1mo ago First seen · 52 lines · 1,357 tokens per session scan A faa97b830529
deepseek-cowork AGENTS.md is an instructions file published in the GitHub repository chuancyzhang/deepseek-cowork (18 stars, last pushed today), licensed Apache-2.0. It adds 2,378 tokens to every session, about $0.0095 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 2026-09-04.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.