deepseek-cowork: Instructions file for Codex

AGENTS.md

deepseek-cowork AGENTS.md is an instructions file for Codex, OpenCode from chuancyzhang/deepseek-cowork. It costs 2,378 tokens per session, scanned A, original, Apache-2.0.

A set of repository instructions for an AI coding agent working on the deepseek-cowork project. It covers local agent details, collaboration rules, change approval, and interface guidelines.

In plain words
What is it for?
It is for guiding code changes, collaboration, and UI or UX work in that project.
Why use it?
It gives the agent project-specific rules so its changes and conversations follow the repository's expectations.

Instructions file for CodexOpenCode

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

This is chuancyzhang/deepseek-cowork's own configuration. It tells Codex and OpenCode how to work on deepseek-cowork 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 deepseek-cowork configures →

Reuse

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.

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

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 deepseek-cowork AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chuancyzhang/deepseek-cowork/agents-md/github.svg)](https://agentmods.dev/instructions/chuancyzhang/deepseek-cowork/agents-md)
Your own site
<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.

agentmods 80×15 button for deepseek-cowork AGENTS.md

Your own site · 80×15
<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>
Per session 2,378 This file is loaded in full into every session.
When invoked 2,378 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 $0.02378 $0.02378
Opus 5.5 $0.00951 $0.00951
Sonnet 5.5 $0.00476 $0.00476
Haiku 4.5 $0.00238 $0.00238

Measured 3d ago against content hash 26e59aafafdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

AGENTS.md · 124 lines

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

Read the full file on GitHub · 124 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. 3d ago Changed · -2 lines · -54 tokens per session 26e59aafafdc
  2. 11d ago Changed · +1 lines · +21 tokens per session 1d84c4ad97e5
  3. 1mo ago Changed · +73 lines · +1,054 tokens per session 78fbd3d183c0
  4. 1mo ago First seen · 52 lines · 1,357 tokens per session scan A faa97b830529

Subscribe to this mod's changes

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.

Related

Other instructions, from other repositories