How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
RyanAlbertsCLAUDE.mdRyanAlberts/best-of-Agent-Harnesses/CLAUDE.md
Repo notes for AI coding agents ## Commit identity (required) All commits in this repo must be authored as: - **Name:** `Ryan Alexander Alberts` - **Email:** `25306145+RyanAlberts@users.noreply.github.com` — GitHub's noreply address
shanraisshanCLAUDE.mdshanraisshan/codex-cli-best-practice/CLAUDE.md
claude-code-hooks](https://github.com/shanraisshan/claude-code-hooks). ## Architecture The repo demonstrates four interconnected systems: 1. **Config** (`.codex/config.toml`) — TOML-based layered config with 5 profiles (conservative, development, trusted, ci, review), MCP server
routaticCLAUDE.mdroutatic/proxy/CLAUDE.md
system/plan review → invoke /design-consultation or /plan-design-review - Full review pipeline → invoke /autoplan - Bugs/errors → invoke /investigate - QA/testing site behavior → invoke /qa or /qa-only - Code review/diff check → invoke /review - Visual polish → invoke /design-review
zhu1090093659CLAUDE.mdzhu1090093659/spec_driven_develop/CLAUDE.md
agents. Claude Code-specific reminders: - The optional Claude Code sub-agent prompts live in `plugins/spec-driven-develop/agents/`, including `code-reviewer.md`, the per-lane review-and-fix sub-agent used in the execution loop
Pantheon-SecurityCLAUDE.mdPantheon-Security/medusa/CLAUDE.md
python-expert** - Python & YAML processing 2. **ai-security-researcher** - AI/ML security expert 3. **code-reviewer** - Code quality & security review 4. **test-engineer** - pytest, coverage, CI testing **Release & Distribution:** 5. **github
bitjaruCLAUDE.mdbitjaru/styleseed/engine/CLAUDE.md
build UI, running this setup is the **FIRST thing you do — before any code.** Skipping it is exactly how the output lands generic (default indigo, tight type, template layout
agentic-communityCLAUDE.mdagentic-community/mcp-gateway-registry/CLAUDE.md
TEAM.md). This persona provides comprehensive guidelines for: - Running and verifying tests - Assessing code quality against these standards - Reviewing architecture and design decisions - Checking for breaking changes - Evaluating performance impact - Ensuring
luongnv89CLAUDE.mdluongnv89/asm/CLAUDE.md
TypeScript CLI plus ink/React TUI that manages Agent Skills installed for Claude Code, Codex, Gemini, and OpenClaw. ## Critical commands ```bash npm install # postinstall no-ops when CI or ASM_SKIP
PipelexCLAUDE.mdPipelex/pipelex/CLAUDE.md
CONTRACT= RATIONALE="…"`. No bypass flag; "reviewed, no doc change needed" is a legitimate rationale. See `docs/contribute/drift-contracts.md`. - **`make agent-test` at the end of every coding session.** Heartbeat lines while running
apifyCLAUDE.mdapify/mcpc/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
opentabs-devCLAUDE.mdopentabs-dev/opentabs/CLAUDE.md
This is the last gate before code enters the repository — treat it as a code review, not a formality. - **Read the full diff** (`git diff` for unstaged, `git diff --cached
voicetreelabCLAUDE.mdvoicetreelab/voicetree/backend/claude.md
there is a less complex alternative. when planning a task that involves writing code: First research review the existing code. Think about the best way to structure the solution, such
solatisCLAUDE.mdsolatis/claude-config/conventions/CLAUDE.md
definitions | Understanding QR severity, writing QR scripts | | `structural.md` | Code quality conventions, testing rules | QR code review, planner decision audit | | `temporal.md` | Timeless present rule for comments | TW/QR temporal contamination checks, writing
solatisCLAUDE.mdsolatis/claude-config/skills/CLAUDE.md
Planning and execution workflows | Creating implementation plans | | `refactor/` | Refactoring analysis across dimensions | Technical debt review, code quality | | `problem-analysis/` | Structured problem decomposition | Understanding complex issues | | `decision-critic/` | Decision stress-testing
umputunCLAUDE.mdumputun/revdiff/CLAUDE.md
runtime; a CLI lacking `get` abandons a live review); `pane zoom` is unprobed as cosmetic. The wait loop treats `{"error":{"code":"pane_not_found"}}` as authoritative death (nothing closed, nothing
AnthropicCLAUDE.mdanthropics/buffa/CLAUDE.md
buffa-types/src/generated/` shows as modified, you forgot to commit the regen. ## Pre-Commit Code Review Before producing a commit, run **both** review agents in parallel (single message, two Agent
MicrosoftCLAUDE.mdmicrosoft/fabric-toolbox/tools/MicrosoftFabricMgmt/CLAUDE.md
# CLAUDE.md - MicrosoftFabricMgmt Module Development Guide ## Overview This document provides comprehensive instructions for AI-assisted
jdevalkCLAUDE.mdjdevalk/specification.website/CLAUDE.md
Astro site, deployed to Cloudflare Pages from this repository's `main` branch. MIT licensed (code) / CC BY 4.0 (content). Live: <https://specification.website> and <https://specification-website.pages.dev>. ## Top-level rule: everything
LeslieLeungCLAUDE.mdLeslieLeung/glean/backend/CLAUDE.md
backend/packages/database/glean_database/models/` 2. Create migration: `make db-migrate MSG="add_field_to_table"` 3. Review generated migration in `migrations/versions/` 4. Apply: `make db-upgrade` **Alembic Best Practices**: - Never manually edit migration
alirezarezvaniCLAUDE.mdalirezarezvani/claude-code-skill-factory/CLAUDE.md
your current task context, giving you focused guidance without information overload. --- ## Repository Structure ``` claude-code-skills-factory/ ├── README.md # Project overview and quick start ├── CLAUDE.md # This file - orchestration layer ├── .github/ │ ├── 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.
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.
