How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
modoojunkoCLAUDE.mdmodoojunko/awesome-novel-agent/templates/CLAUDE.md
本项目的写作流程由 9 个 agent 协作完成，定义在 .claude/agents/ 下。 开始写作： 输入 @novel-agent 进入写作循环。 写作流程： 设定 →（作者确认）→ 卷纲 →（作者确认）→ 章纲 →（作者确认）→ 提示词 → 正文 → 验收 → 归档 → 下一章 灵魂与笔墨： 设定、卷纲、章纲是故事的灵魂，每一步都先给作者看摘要、等作者点头才继续；提示词之后的正文与打磨是 AI…
alirezarezvaniCLAUDE.mdalirezarezvani/claude-code-tresor/CLAUDE.md
For Claude Code instances working with Claude Code Tresor Claude Code Tresor is a comprehensive collection of professional-grade utilities for Claude Code: - 8 Autonomous Skills: Automatic background helpers (NEW in v2.0!) - 8 Core Agents: Production-ready expert sub-agents for deep analysis - 133 Extended Agents: Specialized agents organized by team and function (v2.5+) - 19 Slash Commands: Workflow automation and intelligent orchestration (NEW v2.7!) - 4 Development commands - 5 Tresor Workflow commands - 10 Orchestration commands (Security, Performance,…
bruin-dataCLAUDE.mdbruin-data/dac/CLAUDE.md
Bruin is an engineering-grade data tool that presents information with authority. The UI should feel like it knows what it's doing — no unnecessary decoration, no hand-holding, no visual noise.…
unbrowse-aiCLAUDE.mdunbrowse-ai/unbrowse/CLAUDE.md
READ ~/.claude/AGENTS.md BEFORE ANYTHING (skip if missing). Open-source client for the hosted Unbrowse REST API (/api/v1) and remote MCP. No browser, no site logic; unbrowse mcp is only a stdio proxy to the hosted MCP. Commands: bun install · bun test ./packages ./tests · bun run check:plugins · bun run typecheck · bun run build · bun run cli help. Rules: - A new API route gets an SDK method and a row in packages/sdk/tests/client.test.ts; a CLI command maps to…
CodeBendKitCLAUDE.mdCodeBendKit/codeseek/CLAUDE.md
The process binds to exactly one repository at startup via --repo-path. StorageManager.currentrepo tracks this. trybindrepo() rejects attempts to switch repos. The HTTP API no longer accepts repopath/project_dir parameters — all endpoints use the bound repo.
taekchefCLAUDE.mdtaekchef/claude-code-zh-cn/CLAUDE.md
Claude Code CLI 中文本地化插件。 翻译数据单一来源，不允许重复维护： 禁止把 verbs 或 tips 的内容复制到 settings-overlay.json 里。如果要修改翻译，只改 verbs/ 或 tips/ 里的文件。 每完成一批有意义的改动后，按以下步骤发布新版本：
Kc1tCLAUDE.mdKc1t/alethe-agents/CLAUDE.md
Identical in content to AGENTS.md in this directory. Keep both in sync. Contributing from outside? Start with CONTRIBUTING.md — setup, project layout, house rules, and PR convention. Alethe is a…
undefined-uiCLAUDE.mdundefined-ui/second-brain-os/vault-template/CLAUDE.md
You maintain this vault. The owner drops raw material into raw/ and asks questions. Everything in wiki/ is yours to write and keep correct. The wiki is the primary artifact. raw/ is an archive you can always re-read, but nobody reads it day to day. If something matters, it has to end up on a wiki page, in your own words, linked to everything related. Never write to raw/. Never delete a wiki page without recording it in log.md first,…
Archive228CLAUDE.mdArchive228/loopkit/.claude/CLAUDE.md
@../AGENTS.md
SentryCLAUDE.mdgetsentry/sentry-rust/CLAUDE.md
Use rust-analyzer-mcp for local code (hover, definitions, diagnostics at file positions). Use crates-mcp for external crate docs. Never use WebFetch for docs.rs or crates.io when these MCPs are available.
divar-irCLAUDE.mddivar-ir/ai-doc-gen/CLAUDE.md
See AGENTS.md for project instructions (commands, architecture, conventions, gotchas). Claude-specific notes:
dondai44423CLAUDE.mddondai44423/donsetch/CLAUDE.md
No summary in the file. Open it to read it.
ShopifyCLAUDE.mdShopify/cli/.claude/CLAUDE.md
See @../AGENTS.md for repository-specific agent instructions.
nexu-ioCLAUDE.mdnexu-io/motion-anything/CLAUDE.md
This project follows a single, tool-agnostic working agreement so it can be continued by any AI agent in any session. 👉 Read AGENTS.md first — it is the source of truth for repo structure, the recipe manifest schema, the golden path for adding recipes, and the hard rules. 👉 Then read PROGRESS.md — current status and the task queue. 👉 The motion standard is MOTION-SPEC.md — every recipe and the router skill must obey it. - This repo is intentionally…
CryptoDmitryCLAUDE.mdCryptoDmitry/Ghost-Agent/CLAUDE.md
This is the Ralph for Claude Code repository - an autonomous AI development loop system that enables continuous development cycles with intelligent exit detection and rate limiting. Version: v0.9.8 | Tests: 276 passing (100% pass rate) | CI/CD: GitHub Actions The system consists of four main bash scripts and a modular library system: The system uses a modular architecture with reusable components in the lib/ directory:
memex-labCLAUDE.mdmemex-lab/memex/CLAUDE.md
AGENTS.md is the canonical instruction file for coding agents in this repo. Read it before editing code, and follow its architecture, data-access, localization, logging, and testing requirements. If this file…
ZhangHanDongCLAUDE.mdZhangHanDong/makepad-skills/CLAUDE.md
These concept anchors provide design judgment for Makepad 2.0 architecture questions. Use them when facing "how should I organize state / split components / handle complex interactions" — questions without…
jame581CLAUDE.mdjame581/GodotPrompter/CLAUDE.md
This is a documentation/skills repository. There is no application build/lint, but node scripts/validate-skills.mjs checks SKILL.md frontmatter, cross-references, and structure — validate.yml runs it plus npm test on every PR and push to master, and release.yml again on the tag. Otherwise, changes are validated by reading skills, verifying code examples in Godot 4.3+, and running the agent integration tests in tests/agent-integration/TEST_PLAN.md. The layout is self-evident from ls; these constraints are not:
MicrosoftCLAUDE.mdmicrosoft/TypeAgent/ts/examples/planValidationDemo/CLAUDE.md
This project is governed by a plan-validation MCP server. *Every file access and shell call you make must go through the validated_ tools.** The built-in Read, Write, Edit, Bash, Glob, Grep tools are NOT available in this session — only the MCP tools provided by the plan-validation server. A live dashboard is running at http://localhost:3100 — every tool call you make is visible there, including blocks. Call getplanschema. Read it carefully — the AgentPlan DSL has strict shape requirements and…
MicrosoftCLAUDE.mdmicrosoft/TypeAgent/ts/packages/agents/powershell/CLAUDE.md
PowerShell captures and reuses PowerShell scripts from reasoning traces. Scripts persist in instance storage (~/.typeagent/profiles/<profile>/powershell/) across sessions. Grammar rules are registered dynamically at runtime — no build step needed for user-created flows. scripts/compileRecipes.mjs reads pending/*.recipe.json and generates build-time artifacts. This is useful for testing but not used in production — production flows are loaded from instance storage at runtime.
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.
