CoCoWork: Instructions file for Claude Code

CLAUDE.md

CoCoWork CLAUDE.md is an instructions file for Claude Code from NUGURI-7/CoCoWork. It costs 2,789 tokens per session, scanned A, original, MIT.

Project instructions for CoCoWork, covering its coding preferences, file responsibilities, project notes, and approval process.

In plain words
What is it for?
Use them to plan changes, check context files, request approval, follow production-quality coding standards, and maintain the project's structured notes.
Why use it?
They prevent an agent from changing code before approval and keep project context, backend work, frontend work, and learning notes organized.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is NUGURI-7/CoCoWork's own configuration. It tells Claude Code how to work on CoCoWork 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 CoCoWork configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NUGURI-7/CoCoWork. 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/NUGURI-7/CoCoWork/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/NUGURI-7/CoCoWork

Made for: Claude Code.

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 CoCoWork CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nuguri-7/cocowork/claude-md.svg)](https://agentmods.dev/instructions/nuguri-7/cocowork/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nuguri-7/cocowork/claude-md"><img src="https://agentmods.dev/badge/instructions/nuguri-7/cocowork/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,789 This file is loaded in full into every session.
When invoked 2,789 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 $0.02789 $0.02789
Opus 5 $0.01394 $0.01394
Sonnet 5 $0.00558 $0.00558
Haiku 4.5 $0.00279 $0.00279

Measured 8d ago against content hash 963c375c888b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

CoCoWork CLAUDE.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 8d 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.

CLAUDE.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Global User Preferences

  1. Prefer production-grade, industry-standard solutions over quick fixes or ad hoc hacks. When a widely accepted standard approach exists, use it instead of inventing a custom workaround.
  2. 所有任务动手前都需要先描述步骤/方案,等用户审批后再编写代码。对于架构设计、模块搭建、技术选型等复杂任务,代码方案需额外经过一轮审批后才能写入文件。
  3. If the user's request is ambiguous or missing key details, ask clarifying questions before writing code.
  4. 每次开始新任务时,如果存在 docs/context.md,先读取它。
  5. 每次完成有意义的项目改动后,更新 docs/context.md,同步最新的当前状态。
  6. 保持 docs/context.md 精简:优先重写摘要,只保留最近迭代,并将更早内容压缩进历史摘要。
  7. 记笔记 触发词:当我说「记笔记」时,把当前对话里值得沉淀的概念 / 决策 / 踩坑写进学习笔记。判断值不值得记,只看 notes/README.md 定的三条目标:复习自测 / 防遗忘 / 面试备忘 —— 即「将来我复习这个项目、或别人针对这个项目问起时用得上」,不是「离开这个项目还成立的通用道理」;沟通方式、Claude 自己的思维过程一律不记。笔记模块固定在项目根目录下的 notes/notes/backend/<模块>/notes/frontend/<模块>/,每个模块含 notes.md + qa.md,遵循既有 frontmatter + TL;DR + 编号要点 / QA 风格),不用每次现找目录。写之前先列出「打算记哪些条目」让我审批,审批通过再落盘,不要直接写。优先追加到已有模块笔记、避免重复,不轻易新建目录。
  8. 代码默认生产级最终版:每次落盘的首版即架构 / 命名 / 扩展性 / 类型 / 异常一次到位;不分"先简后繁"、不写阶段化占位(P0/P1、# TODO 这版先这样)。小步迭代是任务分段,不是代码风格分段。

代码分工(谁动文件)

所有代码都由 Claude 落盘(Write/Edit),用户不手敲。 但前后端的审批方式不同:

后端 —— 必须看代码。 落盘前把完整代码贴在对话里,按下面「给代码的方式」带用户读一遍,用户点头之后才动文件。未经审批不许落盘。

前端 —— 不看代码。 落盘前只说清「要做什么、动哪几个文件」,得到许可即可直接写,不要把前端代码贴出来(用户不 review 前端)。

单元测试例外:写完直接跑,只汇报结果,不必事先申请。

数据库迁移:禁止手写迁移文件正文 —— 先改 model,再 uv run tortoise makemigrations -n xxx 用 CLI 生成,生成结果给用户过目。

拿不准归哪类时,先问,不要默认落盘。

给代码的方式(不给孤立函数)—— 只适用于后端

给我看后端代码时,按「我要顺着你的话在文件里找到它」来写,不要甩一段孤立函数让我自己找位置:

  1. 先说打开哪个文件、改哪一段(带行号锚点)。

  2. 已有文件一律给「原来长这样 → 改成这样」,前后留几行原代码当路标;只有新增文件才给完整全文。

  3. 说清为什么改这里,以及它跟谁有关系(谁调它、参数从哪来、改完谁受影响)。

  4. 贴完代码,再用自然语言把这段逻辑讲一遍 —— 按执行顺序说清每一步在干 什么、失败会怎样、为什么是这个顺序。讲在对话里,不许塞进代码注释: 注释密度保持原样,讲述是给我看的、不是给代码看的。

    理由:我现在看不下去纯代码细节了。第 1-3 条解决「这段代码在哪」, 第 4 条解决「这段代码在干嘛」—— 后者才是我真正在审的那一份。

目的:后端代码全部由 Claude 落盘,所以「审」是我唯一一次看见它的机会 —— 我是这个项目唯一的维护者,出了 bug 得自己知道去哪儿看。审不明白等于没写。

CoCoWork — Claude Code 指南

AI Agent 管理平台(暂定方向,随开发推进持续演化):基于 LangGraph + FastAPI + PostgreSQL(pgvector)+ Redis 构建后端,React 19 + shadcn/ui 构建前端。核心能力包括:多 Agent 编排与调度、RAG 混合检索(向量 + 全文检索 + 重排序)、Skill 技能市场、知识库管理;支持语音交互(ASR/TTS)与视觉理解多模态输入输出;提供多层 RBAC 权限管控与资源隔离。定位为可管理、可编排、可扩展的一站式 Agent 平台。

Read the full file on GitHub · 166 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. 8d ago First seen · 166 lines · 2,789 tokens per session scan A 963c375c888b

Subscribe to this mod's changes

CoCoWork CLAUDE.md is an instructions file published in the GitHub repository NUGURI-7/CoCoWork (15 stars, last pushed 7d ago), licensed MIT. It adds 2,789 tokens to every session, about $0.0139 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.

Related

Other instructions, from other repositories

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 · 7,296 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

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.

github/spec-kit · 7,104 tokens