How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
ZhangHanDongCLAUDE.mdZhangHanDong/harness-engineering-from-cc-to-ai-coding/CLAUDE.md
specs/writing-plan.md` — 写作执行计划，含依赖图和批次安排 编写任何章节前，先读对应的 spec 文件。大纲在 `docs/book-outline.md`。 ## 项目结构 ``` restored-src/src/ # Claude Code v2.1.88 还原的 TypeScript 源码（只读，不修改） book/ # mdbook 书籍项目 book.toml # mdbook 配置 src/ SUMMARY.md # 目录结构
Open-Source-LegalCLAUDE.mdOpen-Source-Legal/OpenContracts/CLAUDE.md
utility files: - **Before writing new utilities**: Check existing utility files first (`frontend/src/utils/`, `opencontractserver/utils/`) - **When reviewing code**: If you find utility functions defined inline in components/views, check if they already exist
umputunCLAUDE.mdumputun/ralphex/CLAUDE.md
buildPreviousContext()`, prompt assembly - `pkg/processor/phase/external_review.go` - tool selection and external review loop ### Alternative Providers for Claude Phases `claude_command`/`claude_args` replace Claude Code with any `stream-json`-compatible CLI. Included wrappers
HexmosTechCLAUDE.mdHexmosTech/git-lrc/CLAUDE.md
authenticated against `HexmosTech/git-lrc` for `make release-gh`. ## Sequence 1. **Land the code change first.** Stage, review (or skip), commit, and push *before* touching the version: ``` git add git lrc review
win4rCLAUDE.mdwin4r/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
daymadeCLAUDE.mddaymade/claude-code-skills/CLAUDE.md
Bundled resources** - Loaded as needed by Claude ## Development Commands ### Installation Scripts **In Claude Code (in-app):** ```text /plugin marketplace add daymade/claude-code-skills ``` Then: 1. Select **Browse and install plugins** 2. Select
daymadeCLAUDE.mddaymade/claude-code-skills/daymade-skill/CLAUDE.md
This directory bundles skills related to Claude Code skill development, quality, and governance. ## Included Skills - `skill-creator` — Create and improve skills. - `skill-reviewer` — Review skill quality and trigger accuracy. - `skills
plugin87CLAUDE.mdplugin87/ux-ui-agent-skills/CLAUDE.md
behind /critique .claude/skills/ ← Runnable skills (invoke via /name): design-tokens, design-component, design-code, design-review, a11y-audit, apply-aesthetic, redesign, data-dashboard, migrate-design-system, prototype, ux-writing, governance
yohey-wCLAUDE.mdyohey-w/multi-agent-shogun/CLAUDE.md
Claude Code + tmux multi-agent parallel dev platform with sengoku military hierarchy
CloudAI-XCLAUDE.mdCloudAI-X/claude-workflow-v2/CLAUDE.md
agents: | Task | Agent to Use | | ------------------ | ------------------ | | Multi-file changes | `orchestrator` | | Code quality check | `code-reviewer` | | Bug investigation | `debugger` | | Update docs | `docs-writer` | | Security review | `security-auditor` | | Clean up code | `refactorer
tigerless-labsCLAUDE.mdtigerless-labs/agent-memory/CLAUDE.md
green-CI PR handed off for review — the owner merges, never the agent. ## Working rules - **English only in commits, PRs, issues, and code identifiers.** Design docs under `docs/design/` may stay
nrslibCLAUDE.mdnrslib/takt/CLAUDE.md
this repository. > **This file is not user-facing documentation.** It exists for Claude Code to read while working in the repository — it does not substitute for the real docs under
m0n0x41dCLAUDE.mdm0n0x41d/haft/CLAUDE.md
read orientation, not a universal first step or gate, and it does not replace code-graph preflight. `known_absent` is an identity result, not permission to persist. When current Work
peterkrueckCLAUDE.mdpeterkrueck/Claude-Code-Development-Kit/templates/CLAUDE.md
complexity, stop and reassess rather than pushing through. - **Use available skills proactively**: `/review-work` for code review, `/update-docs` after significant changes, `/deploy` for deployments. - **Context7 first**: When working with external libraries
elirantutiaCLAUDE.mdelirantutia/vibeyard/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
OpenRaiserCLAUDE.mdOpenRaiser/NanoResearch/CLAUDE.md
Pipeline NanoResearch uses a 9-stage pipeline: ```text IDEATION -> PLANNING -> SETUP -> CODING -> EXECUTION -> ANALYSIS -> FIGURE_GEN -> WRITING -> REVIEW ``` Stage meanings: - `ideation`: literature search, gap finding, hypothesis or theme extraction - `planning
Team-CommonlyCLAUDE.mdTeam-Commonly/commonly/CLAUDE.md
ACCOUNT`) or via ExternalSecrets. - **UI verification**: Use MCP Playwright (`mcp__playwright__*`) ### 📁 Key Documentation Files - **Code Review Rubric**: `/REVIEW.md` — **REQUIRED READING** before any code review, implementation planning, or pre-commit self
jayminwestCLAUDE.mdjayminwest/overstory/CLAUDE.md
configurable (default 2). Prevents runaway spawning. ### Runtime Modes: headless vs tmux (Claude Code) Claude Code agents can run in two modes. **Headless is the shipped default for new projects
sceneviewCLAUDE.mdsceneview/sceneview/CLAUDE.md
every API, doc and sample: can an AI read this and emit working code on the first try? If not, simplify the API or fix the doc until
sipyourdrink-ltdCLAUDE.mdsipyourdrink-ltd/bernstein/CLAUDE.md
offline, from the artifacts alone. CLI coding agents work out of the box (Claude Code, Codex, Gemini CLI, and 52 more), and the same layer governs any agent workload
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.
