alpbahadurCLAUDE.md49-IDE
alpbahadur/49-IDE/CLAUDE.md
NEVER WORK IN MASTER NO MATTER WHAT WHENEVER WORKING ON A FEATURE, MAKE YOURSELF A WORKTREE AND A BRANCH. WORK THERE ONLY. COMMIT FREELY THERE, BUT DO NOT MERGE INTO…
CLAUDE.md examples from real projects
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Most stars first · from page 39Worked for most · soon
alpbahadurCLAUDE.md
hydro13CLAUDE.mdtandem-browser
hydro13/tandem-browser/CLAUDE.md
Read AGENTS.md in full — it is the development guide for coding agents working on this repository: workflow, testing gates, git discipline, context discipline, and the anti-detection architecture rules that must never be violated. Before changing code, also read ARCHITECTURE.md for the layer model and the manager system. Quick facts:
craigscCLAUDE.mdcmux
craigsc/cmux/CLAUDE.md
cmux is a pure Bash shell tool that manages git worktree lifecycles for running parallel Claude Code sessions. Each worktree gets its own isolated working directory so multiple Claude agents can work on the same repo simultaneously. Single-file shell tool — all logic lives in cmux.sh (~560 lines), which is sourced into the user's shell (bash/zsh). There is no build step, no dependencies, and no test suite. Function structure: - cmux() — public dispatcher, routes subcommands to cmux<cmd> functions -…
s0ld13rrCLAUDE.mdpentestcode
s0ld13rr/pentestcode/CLAUDE.md
PentestCode — AI pentesting agent, hard fork of OpenCode (dev branch, MIT). OpenCode — coding agent (183k stars). We stripped code-editing focus and rebuilt it for penetration testing. Stack: TypeScript, Bun, Effect library, Turbo monorepo. TUI: React/Ink (via @opentui). LLM: ai-sdk (20+ providers). DB: SQLite (drizzle-orm). Agents defined in: packages/opencode/src/agent/agent.ts Prompts in: packages/opencode/src/session/prompt/.txt and packages/opencode/src/agent/prompt/.txt
xianyu110CLAUDE.mdawesome-claudcode-tutorial
xianyu110/awesome-claudcode-tutorial/CLAUDE.md
这是一个全面的 Claude Code 中文教程项目，涵盖从入门到精通的所有内容。 每个章节应遵循以下结构： 使用表格进行对比和总结： bash # 命令行代码 npm install javascript // JavaScript 代码 const x = 1; 欢迎贡献！请遵循以下规范：
ZacheryGlassCLAUDE.md.claude
ZacheryGlass/.claude/CLAUDE.md
When committing code changes: - Never add Claude as a commit author. - Always commit as using the default git settings When creating or updating markdown documentation files: - Never…
ww-w-aiCLAUDE.mdbkit-claude-code
ww-w-ai/bkit-claude-code/.claude/CLAUDE.md
Do NOT advance or modify the project version. Version bumps (the version field in .claude-plugin/plugin.json, package.json if any, and version headers) are the repo maintainer's responsibility — not the agent's. This applies to: Sprint Management is a meta-container that groups one or more features under a shared scope, budget, and timeline. Each sprint runs its own 8-phase lifecycle: prd → plan → design → do → iterate → qa → report → archived. When the user mentions "sprint", invoke bkit:sprint…
mnemon-devCLAUDE.mdmnemon
mnemon-dev/mnemon/CLAUDE.md
No summary in the file. Open it to read it.
WoJiSamaCLAUDE.mdskill-based-architecture
WoJiSama/skill-based-architecture/CLAUDE.md
This repo is the skill-based-architecture meta-skill itself. Formal docs live at the repo root (self-hosting layout, see references/layout.md). Read SKILL.md first — it is the router. Task routes live in references/self-hosting-routing.yaml. For every new task: 1. Read SKILL.md. 2. Read references/self-hosting-routing.yaml. 3. Match exactly one route by labels, triggerexamples, and task intent; if none matches, use other. 4. Follow only that route's workflow; the route does not preload project knowledge. 5. Let the workflow inspect the smallest evidence that can…
aitytechCLAUDE.mdagentkits-marketing
aitytech/agentkits-marketing/CLAUDE.md
Your role is to analyze marketing requirements, delegate tasks to appropriate marketing agents, and ensure cohesive delivery of campaigns that drive leads, conversions, and revenue. CRITICAL - DATA RELIABILITY: NEVER fabricate data. Use MCP integrations for real metrics. If data unavailable, show "⚠️ NOT AVAILABLE" with setup instructions. See data-reliability-rules.md for full rules. IMPORTANT: Analyze the skills catalog and activate the skills that are needed for the task during the process. IMPORTANT: You must follow strictly the marketing rules in…
bryanyzhuCLAUDE.mdagentic-ai-system-course
bryanyzhu/agentic-ai-system-course/CLAUDE.md
Note: this file is duplicated at AGENTS.md for tools that look for the universal name (Codex, Cursor, etc.). If you edit one, edit the other — they must stay identical. This file teaches you (Claude Code, Codex, Cursor, or whichever coding agent is reading it) how to act as a learning companion for someone studying Production-grade agentic systems. The course lives in course/. Reference systems can optionally be cloned into references/ for grounded answers — they are not required to…
meodaiCLAUDE.mdskill.color-expert
meodai/skill.color-expert/CLAUDE.md
This file provides guidance when working with code in this repository. This is an agent skill (compatible with Claude Code, Codex, Cursor, Copilot, OpenCode, and others via agentskills.io). It contains…
anombyte93CLAUDE.mdprd-taskmaster
anombyte93/prd-taskmaster/CLAUDE.md
Atlas's entry point is a frontier model (Fable, or whatever the best frontier model is) acting as the driver. The driver understands the user's intent using skills built for it, then — inside a loop — decomposes the goal into optimal components and routes each to the cheapest capable executor, to save as many tokens as possible while delivering an outcome as good as if the frontier model had done all the work itself, at a fraction of the cost.
FradSerCLAUDE.mddotclaude
FradSer/dotclaude/CLAUDE.md
This is a Claude Code plugin marketplace (frad-dotclaude) containing 21 plugins across development and productivity categories. Each plugin follows auto-discovery conventions—place components in commands/, agents/, skills/ directories and Claude discovers them automatically. Active plugins: git, github, refactor, swiftui, office, lark, hyperframes, plugin-optimizer, mattpocock, superpowers, antigravity, pi, interfaces, storm, hardware, autoresearch, memory Non-active plugins: acpx, code-context, utils, meeseeks-vetted Skill registration determines visibility. A skill registered under "commands" in plugin.json becomes a user-invocable slash command (e.g., /git:commit). A skill registered under "skills"…
FradSerCLAUDE.mddotclaude / marketing
FradSer/dotclaude/marketing/CLAUDE.md
Guidelines for AI agents working in this repository. This repository contains Agent Skills for AI agents following the Agent Skills specification. Skills install to .agents/skills/ (the cross-agent standard). This repo also serves as a Claude Code plugin marketplace via .claude-plugin/marketplace.json. Skills are content-only (no build step). Verify manually: - YAML frontmatter is valid - name field matches directory name exactly - name is 1-64 chars, lowercase alphanumeric and hyphens only - description is 1-1024 characters CLI tools (tools/clis/*.js) are zero-dependency…
paperboytmCLAUDE.mdspool
paperboytm/spool/CLAUDE.md
Always read DESIGN.md before making any visual or UI decisions. All font choices, colors, spacing, layout, and aesthetic direction are defined there. Do not deviate without explicit user approval. Key…
zhsamaCLAUDE.mdclaude-sub-agent
zhsama/claude-sub-agent/CLAUDE.md
Claude Sub-Agent Spec Workflow System - A comprehensive AI-driven development workflow system built on Claude Code's Sub-Agents feature. This system transforms project ideas into production-ready code through specialized AI agents…
biaogebusyCLAUDE.mdweb-builder
biaogebusy/web-builder/CLAUDE.md
Xinshi (信使) Web Builder — an AI-powered low-code platform for building modern responsive web applications. Built with Angular 20 (standalone-only, zoneless, SSR) + Angular Material + TailwindCSS, using Drupal as…
christopherkaraniCLAUDE.mdSwarm
christopherkarani/Swarm/CLAUDE.md
Guidance for AI coding assistants (Claude Code, Cursor, etc.) working in this repository. This file is the canonical, in-repo briefing — read it before making changes. Swarm is a Swift 6.2 framework for building agents and multi-agent workflows on Apple platforms (iOS 26+, macOS 26+, tvOS 26+) and Linux. It is built around: - Agents — Agent struct with @ToolBuilder trailing closures, an AgentRuntime protocol, and pluggable inference providers. - Workflows — fluent composition (.step, .parallel, .route, .repeatUntil) compiled to…
gglucassCLAUDE.mdheadroom-desktop
gglucass/headroom-desktop/CLAUDE.md
This file holds only what the model cannot derive: project invariants, environment quirks, and concrete commands. Generic coding-style coaching (write simply, read before editing, state the bug and stop) was removed on 2026-08-03 — modern models do it unprompted and the harness enforces the rest. Do not re-add it.
About CLAUDE.md
What is CLAUDE.md?
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
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.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.