cindy: Instructions file for Codex

AGENTS.md

cindy AGENTS.md is an instructions file for Codex, OpenCode from makecindy/cindy. It costs 5,519 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for the Cindy desktop and mobile client, including how its rules are organized and which documents govern development, product behavior, design, setup, and security.

In plain words
What is it for?
Use them before working on the Cindy client, especially when setting up the environment or modifying desktop windows, rendering, IPC, navigation, credentials, or stored user data.
Why use it?
They help coding agents respect the repository boundary, locate the right guidance, and avoid changing the separate server repository without permission.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is makecindy/cindy's own configuration. It tells Codex and OpenCode how to work on cindy 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 cindy configures →

About the project

Cindy is an open-source local AI agent that combines coding harnesses, language models, tools, memory, and skills to complete work across files, applications, browsers, computers, and phones. Its desktop and mobile client lets users switch between Claude Code, Codex, other models, and connected services while keeping task context continuous. The catalogue instructions relate to operating or developing this agent.

makecindy/cindy · 6,550 stars · on GitHub · cindy.app

Reuse

Borrowing it

Nothing to install: this file belongs to makecindy/cindy. 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/makecindy/cindy/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/makecindy/cindy

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 cindy AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/makecindy/cindy/agents-md"><img src="https://agentmods.dev/badge/instructions/makecindy/cindy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,519 This file is loaded in full into every session.
When invoked 5,519 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 $0.05519 $0.05519
Opus 5.5 $0.02208 $0.02208
Sonnet 5.5 $0.01104 $0.01104
Haiku 4.5 $0.00552 $0.00552

Measured 2d ago against content hash 130dff5a4c13, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cindy 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 2d 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 · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cindy 客户端仓:Agent 工作入口

本文件是 Codex 与 Claude Code 共用的项目指令正本。CLAUDE.md 只保留 @AGENTS.md,不要在两处重复维护规则。

仓库边界

  • 本仓库只负责 desktop、mobile 及其共享 packages。
  • 服务端位于独立仓库;除非用户明确要求,不要跨仓修改服务端。
  • 开始工作前先检查工作区状态和相关源码,不覆盖、不回退用户已有改动。

规则组织

  • 开发与工程规则统一放在 docs/dev-rules/。
  • 产品行为与体验规则统一放在 docs/product-rules/。
  • UI 视觉、交互与内容设计规则统一放在 docs/design-rules/,权威视觉规范正文为 docs/design-rules/DESIGN.md(根目录 DESIGN.md 仅为跳转入口),目录索引为 docs/design-rules/cindy-design-system.md。
  • 根 AGENTS.md 只保留所有任务都适用的规则、风险入口和文档索引。
  • 目录或模块专属规则优先放到对应目录的嵌套 AGENTS.md;需要跨目录复用的 专题说明放在 docs/,并由本文件写明触发条件。

按模块进入

开发、启动、调试或验证对应模块前,先读下表入口,再按改动触发条件读专题;根级规则始终适用。 跨模块行为先从仓库地图的行为导航查找公共入口与测试, 不要只修改最先找到的页面或渠道。

修改范围 模块规则入口 开发与架构正本
Desktop:main、renderer、preload、数据库、个人 IM / 官方 hook apps/desktop/AGENTS.md Desktop 开发
Mobile:Expo 页面、远程调用、原生配置与模块 apps/mobile/AGENTS.md Mobile 开发与冷更边界
maker-core:Agent 编排、prompt、工具、translator、用量 packages/maker-core/AGENTS.md Agent 行为

当前规则索引

  • 首次接触本仓、需要定位功能代码位置或判断新代码归属模块时,先读仓库地图 docs/dev-rules/repo-map.md。
  • 只为检查界面而需要启动 Desktop 或 Mobile 模拟器、且不需要真实账号时,用 --mock 免登录模拟数据启动;新增或修改模拟任务、--mock 行为前先读 docs/dev-rules/ui-mock-data.md。
  • 首次安装、修复依赖或准备新 worktree 时,必须先读 docs/dev-rules/environment-setup.md。
  • 首次理解模型配置架构,新增模型/供应商,更新模型窗口/价格/推理档位/默认值/本地推荐, 或排查目录下发与显示错误前,必须先读 docs/dev-rules/model-catalog-maintenance.md: 先看结构、覆盖顺序与修改位置,再按其中导航读取专题规则和实际代码;Server 正本与客户端 离线副本需协调更新,客户端已支持、Server 已实现和生产已部署必须分别核验。
  • 修改凭证或授权信息处理、文件落盘位置、用户持久数据、临时文件或测试目录前,必须 先读 docs/dev-rules/credentials-and-local-storage.md。
  • 新增或修改媒体生成、导入、缓存、附件、持久化、协议解析或回收逻辑前,必须先读 docs/dev-rules/media-storage-and-protocols.md。
  • 新增或调整产品功能、判断能力应进入 Core / Skill / 插件、设计人机交互或多端体验 前,必须先读 docs/product-rules/core-product-principles.md。
  • 新增或修改 Agent 管理用户自己的任务、定时任务、项目、伙伴的工具(cindy_helper / cindy_scheduler 等),或调整工具索引、工具的作用范围说明前,必须先读 docs/product-rules/agent-user-parity.md:用户本人能做的(含跨电脑)Agent 也要能做并能在 索引第一步发现;改完把现状台账写回去。
  • 修改共享任务、跨账号访客邀请、共享上下文或共享成员权限前,必须先读 docs/product-rules/shared-task-mode.md;复用 device-link,同账号远控行为不变。
  • 修改 IM 工具授权、来源消息、多端确认或暂停期间的确认回执,或新增 IM 渠道前, 必须先读 docs/product-rules/im-permission-confirmation.md;Desktop、Mobile 与共享 packages 共用同一最终决定,渠道收到回答不代表执行已恢复。
  • 新增或修改代输入(request_input_handoff、宿主步骤读取与执行、代输入卡、终端 askpass、 单窗口实时画面、设备码识别,或任何经手主人填写值的路径)前,必须先读 docs/product-rules/input-handoff.md:主人填写的值只交给宿主执行,不进模型、记录、日志、IM 与推送。
  • 修改账号用量上限的判定、重置时刻来源,或普通任务/目标模式撞上限额后的等待与自动继续前, 必须先读 docs/product-rules/usage-limit-auto-continue.md。
  • 新增或修改自动发送/远程发送消息的路径、消息来源标签,或发给模型的来源说明前,必须先读 docs/product-rules/message-source.md:界面标签与模型说明同源,两侧一起改。
  • 修改伙伴(Bot)的身份、Session 生命周期、模型 fallback、工作目录、Skill / MCP 装配、 委派协作或伙伴设置前,必须先读 docs/product-rules/cindy-bots-runtime.md。
  • 修改伙伴调用任务写工具的身份判定(主人代办 / 受托 / 自主)、自主轮可做的范围、转达主人原话的 核实凭证,或伙伴提示词里对应的说法前,必须先读 docs/product-rules/teammate-authority.md。
  • 修改伙伴的跨电脑身份、主力电脑(登记、接管、交出、降级)、云端对话层与资料上传,或 apps/desktop/src/main/companion-cloud/、Chat Server 的伙伴 actor/1:1 房间合同前,必须先读 docs/product-rules/cloud-companions.md。
  • 新增或修改伙伴群聊的数据、发言编排、群专线 Session、分工(负责人、安排、分工 Session、群工作目录)、 群聊界面或手机端群聊(bot-groups 远程资源、群推送深链)前,必须先读 docs/product-rules/bot-group-chat.md。
  • 新增或修改 /review、Reviewer 任务、成果快照、Finding 协议、复核入口、结果呈现或 复核生命周期前,必须先读 docs/product-rules/review-product-direction.md。
  • 新增或修改按区域(cn / global)分支的逻辑、构建身份与命名、端点选择、区域相关 UI 标注,或涉及两个版本关系的对外文案前,必须先读 docs/product-rules/region-and-editions.md:无限定词身份归 Global,未显式指定 区域一律落在 global,只标注中国大陆版。
  • 新增或修改供应商分享(把远程供应商分享给其他账号)、分享链接、分享申请与审批、 分享管理页,或受邀者使用分享供应商的任何路径前,必须先读 docs/product-rules/provider-sharing.md;它为远程 Agent 通道新增跨账号授权,并允许 中国大陆版与 Global 互享,与共享任务是两套独立授权。
  • 新增或修改供应商组(把多台电脑上的同一个供应商合成一组)、组策略、组内电脑的添加与状态、 经供应商组的任务分配或转发,或「远程与分享」页的组与用量前,必须先读 docs/product-rules/provider-groups.md:Agent 始终在被选中的组内电脑上运行,组所在电脑 只选电脑与转发,并负责按使用方隔离。
  • 新增或修改任何界面、组件、布局、样式、动效或 UI 文案前,必须先读权威设计规范 docs/design-rules/DESIGN.md;设计文档索引见 docs/design-rules/cindy-design-system.md。
  • 做 UI 圆角分类或点击目标尺寸审查时,必须同时读 docs/design-rules/DESIGN.md §5 与 docs/design-rules/design-governance.md §13;普通 UI 改动同样适用,不限于设计系统迁移 PR。
  • 新增或修改设计 Token、主题系统、标准 UI 组件(primitive / pattern)、视觉类门禁脚本, 或参与设计系统迁移 PR 前,必须先读治理合同 docs/design-rules/design-governance.md:真相源边界、兼容红线、两级证据合同与 PR 风险分类均以它为准;视觉规则本身仍以 DESIGN.md 为准。
  • 新增或修改任何 UI 文案里的产品术语前,必须先查术语表 i18n/GLOSSARY.md:已裁决 的术语照用,不自造译法;表里没有或拿不准的,在 i18n/glossary.json 加 status: "proposed" 条目再讨论。门禁为 pnpm check:i18n-glossary,规则见 docs/dev-rules/engineering-conventions.md §5.1。
  • 新增或修改任一 Telegram bot 的用户可见行为(命令、消息呈现、收口策略、群行为、 权限口径、附件与表情)前,必须先读能力台账 docs/product-rules/telegram-bot-parity.md: 两个 bot 是两套架构,差异可以有但必须登记在表里;表里标「有意不同」的行不要去 "统一",动它要先推翻对应裁决。改完记得把对应行写回去。
  • 文案里出现任务 / 对话 / 消息这几个词时,必须先读 docs/product-rules/task-and-conversation-naming.md:session 面向用户叫「任务」, 「对话」只用于任务内的交流过程与内容,单条往来叫「消息」;「任务」与 task 同句出现 时必须消解歧义。这三个词的边界拿不准会直接做出用户能看见的不一致。
  • 所有新增或修改的 UI 必须同时实现 Light 与 Dark 两种模式(颜色一律走语义 token, 禁止只适配一种模式的硬编码或条件补丁);只实现一种模式视为未完成。两种模式的实机 目检不是硬性门槛——能目检更好,做不到时如实写明哪种模式未验证,不得把「复用了 themed 样式」当成「双模式已验证」。具体要求以 docs/design-rules/DESIGN.md 的双模式交付门槛 为准。
  • 修改 Orca 多 Agent 协同时,必须先读 docs/dev-rules/orca-team-architecture.md。
  • 修改任何进入模型 system 段的提示词前(无论文件位于哪个模块),必须先读 docs/dev-rules/maker-core-and-agent-behavior.md。
  • 修改 PI harness 集成(packages/maker-core/src/agents/pi/**、pi-host.ts、 piEnvironment.ts)、PI 会话权限/配置/system prompt/桥接,或 PI 相关的上线判断前, 必须先读 docs/dev-rules/pi-harness.md(含设计原则、维护不变量与上线清单)。其中 Pi 原生能力非退化是红线:Pi 原生允许的安装、更新、扩展加载与 Agent 自助修复,Cindy 不得以静态分析、TUI/RPC 兼容提示、内容指纹、宿主审批或新增的“安全增强”为由拒绝、停用 或变成不可逆流程;显式用户命令即授权。Cindy 只能增加可跳过的提示和更顺畅的 GUI,不能让 Cindy Pi 比同版本原生 Pi 更难用。完整裁决见 docs/dev-rules/pi-harness.md「Pi 上游 GUI 非退化红线」。
  • 修改插件(.cindy)运行时、沙箱、权限、能力 slot、面板供片、网络/凭证/文件交接, 或身份卡、管子协议、打包与编写手册前,必须先读 docs/dev-rules/plugin-security-and-authoring.md。其中存量插件兼容是红线:任何 插件系统改动(含批准状态 schema、指纹格式、manifest 校验、安装布局、包格式)都必须 向下兼容——用户升级后什么都不做,已装、已批准、已启用的插件必须照旧可用,绝不允许 要求用户重新安装、重新确认权限或重新配置。做不到就必须自带从旧版数据的自动迁移; 自动迁移也做不到时,必须有明确提示 + 一次性批量恢复入口,且不丢用户已存的凭证与偏好。 漏迁移 = P0,规则正文见该文件第 5 节。改到插件基座(运行时/沙箱、批准状态记录、 能力 slot、打包与内容判据、manifest 契约、装入与权限确认 UI、已装列表投影)的 PR 一律 走白名单确认门,需放行人明确 Approve 才能合并,不看 diff 大小、不因「是 bugfix/纯技术 改动」豁免。
  • 修改插件发现链(花名册注入、ghost_list / ghost_info / ghost_call)、插件运行期 可见性门禁或 FORGE_GUIDE 作者契约前,必须先读 docs/ghost-progressive-discovery.md。
  • 新增或修改插件持久 Library(library 槽、binding / 目录选择、随时迁移、 回收站删除、SQLite 语句门或 /library/ 面板投影)前,必须先读 docs/dev-rules/plugin-library-storage.md。
  • 修改客户端自动更新链路(cindy-updater 或 Electron 侧更新服务)前,必须先读 docs/dev-rules/cindy-updater.md。
  • 新增或修改 Desktop 日志、IPC 错误处理、main 侧业务逻辑与测试、跨平台(macOS/ Windows)行为,或任何 UI 文案的 i18n 落地前,必须先读 docs/dev-rules/engineering-conventions.md。
  • 新增或改写任一测试前,必须先读 docs/dev-rules/engineering-conventions.md §3.2「新增测试的价值门槛」。测试必须通过 真实生产入口验证可观察结果,并说明 Bug/规则依据、现有覆盖缺口、最小失败输入和 tier; 没有新的结果、错误、权限、持久化、协议或时序差异时停止增加用例。纯跨文件安全、 权限、协议或设计契约才进入 guard;不得为了覆盖率、测试数量或复制常量/JSX/CSS/ 源码字面量而新增测试。同时遵守该节「性能预算」:新文件单独运行本机 5 秒内并在 PR 填实测耗时;被测模块只加载一次,不在 beforeEach/逐用例 helper 里 vi.resetModules(); 不做 ≥100ms 真实等待;同一模块的用例并入已有文件。pnpm check:test-hygiene 在 CI 阻断违规,基线只减不增,不得手改基线放行。
  • 修改客户端日志采集/脱敏/上报链路(apps/desktop/src/main/log-upload/**)、logger.ts 的 main 日志行格式、崩溃判定或待补传标记前,必须先读 docs/dev-rules/log-upload-and-redaction.md。其中三条是不变量:记录边界(写侧 续行转义与读侧切分是同一条不变量的两半,破坏任一侧即隐私逃逸)、白名单方向 (deny-by-default,不得改成黑名单——调试级别的功能日志是用户内容的主要泄漏源)、 标记代次 + 原子清除(并发实例下仅靠时间戳会误删另一实例刚写的新崩溃标记)。 脱敏规则只增不减,放宽任一条视为隐私变更、需重新评审。
  • 修改本地协议 package、插件分发来源边界或 device-link 协议/relay/隧道 payload/IPC allowlist,或任何改动跨端 wire protocol 前,必须先读 docs/dev-rules/protocol-compatibility.md。
  • 修改 package 依赖方向、main 进程模块加载方式,或主界面布局树结构前,必须先读 docs/dev-rules/architecture-invariants.md。
  • 新增或修改 Settings UI、配置文件、本地偏好、运行时 profile,或 agent/MCP/provider 开关前,必须先读 docs/dev-rules/configuration-and-overrides.md。
  • 新增或修改涉及 workdir 文件、agent 进程、会话数据的功能,新增 IPC channel/推送事件, 或修改 device-link 的重试/超时/断链恢复逻辑前,必须先读 docs/dev-rules/remote-and-mobile-adaptation.md;其中恢复路径改动必须回答该文件的 「故障半径三问」。
  • 在 Cindy 内嵌 worktree 会话里工作、准备提交或直推、或做 code review 前,必须先读 docs/dev-rules/development-workflow.md。

Read the full file on GitHub · 232 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. 2d ago Changed · +2 lines · +63 tokens per session 130dff5a4c13
  2. 3d ago Changed · -15 lines · -429 tokens per session 781cbb1405c4
  3. 7d ago Changed · +5 lines · +137 tokens per session 6e2742f262cb
  4. 10d ago Changed · +9 lines · +258 tokens per session 4e65ea97a898
  5. 11d ago Changed · +3 lines · +79 tokens per session 6b6df2c568ea
  6. 12d ago Changed · +7 lines · +200 tokens per session 3865c1fed34f
  7. 17d ago Changed · +4 lines · +112 tokens per session 2913a80255c5
  8. 18d ago Changed · +7 lines · +187 tokens per session 87abf4f9bafe
  9. 19d ago Changed · +2 lines · +53 tokens per session c913bfc41246
  10. 21d ago First seen · 208 lines · 4,859 tokens per session scan A 8b107cf33b10

Subscribe to this mod's changes

cindy AGENTS.md is an instructions file published in the GitHub repository makecindy/cindy (6,550 stars, last pushed today), licensed Apache-2.0. It adds 5,519 tokens to every session, about $0.0221 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

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,786 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens