sandbox-agent / server
rivet-dev/sandbox-agent/server/CLAUDE.md
No summary in the file. Open it to read it.
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
rivet-dev/sandbox-agent/server/CLAUDE.md
No summary in the file. Open it to read it.
GWUDCAP/cc-sessions/CLAUDE.md
A Claude Code workflow framework that enforces structured AI pair programming through Discussion-Alignment-Implementation-Check (DAIC) methodology. cc-sessions transforms Claude Code into a disciplined workflow system where Claude must discuss approaches before writing code, maintains persistent task context across sessions, and provides specialized agents for complex operations. Available in both Python and JavaScript with complete feature parity.
microsoft/playwright-java/CLAUDE.md
The Java client is a port of the JavaScript client in ../playwright/packages/playwright-core/src/client/. When implementing or changing a method, read the corresponding JS file first and mirror its logic. Project checkouts (including the upstream playwright repo) live in the parent directory (../). Use the gh cli to interact with GitHub. Semantic commit messages: label(scope): description Labels: fix, feat, chore, docs, test, devops Never add Co-Authored-By agents in commit message. Never add "Generated with" in commit message. Never add test plan to…
deepcoldy/botmux/CLAUDE.md
飞书话题群 ↔ AI 编程 CLI 桥接。Daemon 监听飞书消息,每个新话题自动 spawn 一个独立 CLI 进程(Claude Code / Codex / Gemini 等 20+ 种,完整列表见 README)。 ⚠️ *别用裸 node 起 daemon —— 用 bun run daemon:。* 会话存储硬依赖 SQLite 引擎 (node:sqlite 需 Node ≥ 22.13,或任意 bun 的 bun:sqlite),而裸 node 由 exec 时的 PATH 解析,那不是写它的环境:2026-09-08 某次 restart 的 PATH 把 /usr/bin 排在 fnm shim 之前 ⟹ 解析成 v18.20.4 ⟹ *55 个 bot daemon 全部启动即崩,飞书里所有话题看似全丢(57 个 SQLite 库其实完好)。supervisor 自身不需要 SQLite,所以它照常打印「✅ daemon 已重启」* —— 这个失败形状是记在这里的唯一理由:报成功、孩子全灭,看日志前无从分辨。 现在 preflight 会在拆掉现有 fleet 之前*按引擎能力拒绝(逃生阀…
disler/claude-code-hooks-multi-agent-observability/CLAUDE.md
Every hook event will include a sourceapp and sessionid. Use these to uniquely identify an agent. For display purposes, we want to show the agent ID as "sourceapp:sessionid" with session_id…
stripe/stripe-dotnet/.claude/CLAUDE.md
It's ok not to put comments on/in a function if their addition wouldn't meaningfully clarify anything.
fynnfluegge/agtx/CLAUDE.md
A terminal-native kanban board for managing multiple coding agent sessions (Claude Code, Codex, Gemini, Copilot, OpenCode, Cursor, Grok, Antigravity) with isolated git worktrees. Logs are JSON at ~/.config/agtx/logs/agtx.log (daily rotation, RUST_LOG respected).
silverstein/minutes/CLAUDE.md
Your AI remembers the conversations you authorize. Minutes — open-source, privacy-first conversation memory layer for AI assistants. Captures meetings, voice memos, and brain dumps, transcribes locally with whisper.cpp, diarizes speakers, and outputs searchable markdown with structured action items and decisions. Built with Rust + Tauri v2 + Node.js (MCP). Four input modes, one pipeline: - Live recording: minutes record / minutes stop — for meetings, calls, conversations - Live transcript: minutes live / minutes stop — real-time transcription with delta…
NeoLabHQ/context-engineering-kit/CLAUDE.md
Claude Code plugin marketplace with advanced context engineering techniques focused on improving agent result quality. See @README for project overview and @CONTRIBUTING.md for contributing guidelines. review, customaize-agent, ddd, docs, git,…
dvdsgl/claude-canvas/canvas/CLAUDE.md
Use Bun for all development: Canvases communicate via Unix domain sockets:
ZhangHanDong/harness-engineering-from-cc-to-ai-coding/CLAUDE.md
本项目基于 Claude Code v2.1.88 的逆向工程源码,编写一本关于 AI Agent 驾驭工程(Harness Engineering)的技术书籍(29 章 + 4 附录)。 任务契约和实施计划在 specs/ 目录: 编写任何章节前,先读对应的 spec 文件。大纲在 docs/book-outline.md。 章节文件写在 book/src/partN/chNN.md,mdbook 通过 SUMMARY.md 自动组织目录。 编写本书时,AI agent 必须加载以下 skill: 每章开始写作前,必须声明预算(tech-writer skill 的 Step 0): 如果某个论点需要第 4 层深度(production 约束讨论),在预算中显式标注。 源码在 restored-src/src/ 下,关键文件索引见 docs/book-outline.md 附录 A。 绝不修改 restored-src/ 下的任何文件。 每章写完后,按 tech-writer skill 的 Phase 3 执行 3-agent 并行 review: 三个 agent 必须在单条消息中并行启动。
Open-Source-Legal/OpenContracts/CLAUDE.md
OpenContracts is an MIT-licensed enterprise document analytics platform for PDFs and text-based formats. It features a Django/GraphQL backend with PostgreSQL + pgvector, a React/TypeScript frontend with Jotai state management, and pluggable document processing pipelines powered by machine learning models. Stack: Django 4.x + GraphQL (strawberry-graphql) + PostgreSQL + pgvector + Celery Key Patterns:
Open-Source-Legal/OpenContracts/frontend/Claude.md
The design system emphasizes clarity, depth, and delight through subtle animations and thoughtful visual hierarchy.
yigitkonur/cli-continues/CLAUDE.md
continues is a CLI tool that lets users resume AI coding sessions across Claude Code, GitHub Copilot CLI, Gemini CLI, Codex CLI, OpenCode, Factory Droid, and Cursor AI. It reads each tool's native session storage (read-only), extracts context (messages, file changes, tool activity, AI reasoning), and injects it into a different tool as a structured markdown handoff document. Run a single test file: Requires Node.js 22+ (uses built-in node:sqlite for OpenCode parsing). src/types/index.ts
limecloud/lime/CLAUDE.md
本仓库的统一工程规范以 AGENTS.md 为准。 请在开始任何分析、编码、测试、文档更新前,先读取并严格遵循以下仓库级规则:
huangserva/skill-prompt-generator/.claude/claude.md
所有学习成果都存储在 elements.db(1103元素,12领域),但每个skill访问不同的领域: 关键: - intelligent-prompt-generator 使用 prompt_framework.yaml(人像专用框架) - 框架包含:subject(主体)、facial(面部)、styling(造型)、expression(表情)、lighting(光影)、scene(场景)、technical(技术) - 所有字段都是人像专用:eyes, nose, lips, makeup, hairstyle, pose 等 - 风景画、产品、海报不需要这些字段 → 必须用domain expert skills STEP 1: 判断主体(最重要) 首先判断:请求中是否包含人物? YES - 有人物:…
najmuzzaman-mohammad/gawkbot/CLAUDE.md
docs/agents/INSTRUCTIONS.md
win4r/ClawTeam-OpenClaw/CLAUDE.md
clawteam is a Python CLI for orchestrating swarms of CLI coding agents (OpenClaw, Claude Code, Codex, Hermes, nanobot, Cursor, etc.). This repo is win4r/ClawTeam-OpenClaw — a fork of HKUDS/ClawTeam where the default agent is openclaw instead of claude. The +openclaw PEP 440 local identifier in the version (e.g. 0.3.0+openclaw1) must be preserved on bumps. There is no server and no database. All state is JSON files under ~/.clawteam/ (overridable via CLAWTEAMDATADIR). Agents coordinate via the shared filesystem: kanban tasks, per-recipient…
microsoft/fluentui-react-native/CLAUDE.md
See @AGENTS.md for guidance on working with code in this repository.
daymade/claude-code-skills/CLAUDE.md
This is a Claude Code skills marketplace containing production-ready skills organized in a plugin marketplace structure. Most plugins expose one skill for narrow installs; suite plugins expose related skills under shared namespaces for combined installation workflows. Essential Skill: skill-creator is the most important skill in this marketplace - it's a meta-skill that enables users to create their own skills. Always recommend it first for users interested in extending Claude Code. Each skill follows a standard structure: Skills use progressive loading:…
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.