CLAUDE.md examples from real projects

AnthropicCLAUDE.md

claude-code

anthropics/claude-code/CLAUDE.md

Guidance for Claude Code and other coding agents working in this repository. Workflow jobs in this repository that call Claude run with three protections. Keep them when you add or…

GitHubCLAUDE.md

spec-kit / integrations

github/spec-kit/docs/integrations/claude.md

Install Claude Code before setup. The integration key is claude. This integration is declared multi-install safe. See the shared multi-install rules. For an existing Spec Kit project, use specify integration install claude. See integration management for activation, upgrades, and removal. Skills are installed as .claude/skills/speckit-<command>/SKILL.md. Invoke them in Claude's chat, for example /speckit-specify or /speckit-bug-assess for the installed bug extension. By default every Spec Kit skill installed for Claude Code is model-invocable, so its description is always in Claude's context…

VercelCLAUDE.md

next.js / next-13

vercel/next.js/evals/next-upgrade/apps/member-dashboard/next-13/CLAUDE.md

No summary in the file. Open it to read it.

ElasticCLAUDE.md

elasticsearch

elastic/elasticsearch/CLAUDE.md

No summary in the file. Open it to read it.

AnthropicCLAUDE.md

claude-cookbooks / chief_of_staff_agent

anthropics/claude-cookbooks/claude_agent_sdk/chief_of_staff_agent/CLAUDE.md

Output: JSON with monthly_burn, runway_months, total_runway_dollars, quarterly_burn, and burn_rate_daily Remember: As Chief of Staff, you have access to financial data in the financial_data/ directory and can delegate specialized analysis to your subagents (financial-analyst and recruiter).

No other project uses it yet

JetBrainsCLAUDE.md

kotlin

JetBrains/kotlin/CLAUDE.md

CRITICAL: @./.ai/guidelines.md guidelines MUST be followed at all times. Local Preferences: @./.claude/local.md When asked to update memory, you must update ./.claude/CLAUDE.md if it is not specified that another file should…

No other project uses it yet

AnthropicCLAUDE.md

financial-services-plugins

anthropics/financial-services-plugins/CLAUDE.md

Cowork plugins and Claude Managed Agent templates for financial services. Each named agent ships two ways from one source. Run python3 scripts/check.py before committing — it lints every manifest, verifies all system.file / skills.path / callable_agents.manifest references resolve, fails if any agent-plugins/<slug>/skills/ copy has drifted from its vertical-plugins/ source, and rejects non-ASCII bytes in a .ps1 without a UTF-8 BOM. Keep .ps1 files pure ASCII. Windows PowerShell 5.1 — still the default shell on managed Windows — decodes a BOM-less…

GitHubCLAUDE.md

awesome-copilot / templates

github/awesome-copilot/skills/repo-standardizer/templates/CLAUDE.md

Telegraph style. Root rules only.

AnthropicCLAUDE.md

knowledge-work-plugins / slack

anthropics/knowledge-work-plugins/partner-built/slack/CLAUDE.md

This plugin integrates Slack with Claude Code, providing tools to search, read, and send messages in Slack.

No other project uses it yet

GoogleCLAUDE.md

skills / refresh

google/skills/skills/cloud/firebase-basics/references/refresh/claude.md

Follow these steps to refresh Claude Code's local environment, ensuring that their agent skills and plugins are fully up-to-date. Use Claude Code's native plugin manager instead of npx. 1. Update the Plugin: Run the specific CLI command to update the Firebase plugin:

No other project uses it yet

GoogleCLAUDE.md

elephant-goldfish-model

google/elephant-goldfish-model/docs/claude.md

Use Claude Code 2.1.271 or later for omitClaudeMd support. Older versions must not be treated as verified Goldfish isolation environments. Enable the installed plugin with claude plugin enable egm@egm. Start messages with /egm:egm-brainstorm, /egm:egm-draft, or /egm:egm-review. Skills retain disable-model-invocation: true: their absence from automatic skill discovery is expected. The Skill tool refuses these skills, so to run another EGM skill (for example egm-review-loop or egm-resolve during review Stages 7 and 9), read its SKILL.md and follow it in the same…

No other project uses it yet

AnthropicCLAUDE.md

claude-quickstarts / chat-sdk

anthropics/claude-quickstarts/managed-agents/chat-sdk/CLAUDE.md

Long-running Node server (Hono): browser chat with a sessions sidebar (useChat → /api/chat) → Chat SDK web adapter onDirectMessage → one Managed Agents session per conversation, where the conversation ID is the session ID (no mapping, no database; the sidebar is sessions.list, transcript replay is sessions.events.list) → a held session event stream (opened with event_deltas token previews, always on) feeds each fragment back onto the same HTTP response while /api/activity streams the tool calls and thinking the page shows as…

No other project uses it yet

AnthropicCLAUDE.md

claude-quickstarts / knowledge-wiki

anthropics/claude-quickstarts/managed-agents/knowledge-wiki/CLAUDE.md

This directory is a Managed Agents quickstart: it builds a real M&A data room into a knowledge wiki (a versioned memory store) with one dynamic workflow run, and queries it. The runnable artifact is distill_documents_into_knowledge_wiki.ipynb; prompts/ holds the consolidation agents' prompts, the lead agent's prompt and the baseline analyst's prompt, utilities.py the notebook's functions; everything else exists to set that notebook up. When a user asks you to walk them through setting this quickstart up, read skill.md in this directory…

No other project uses it yet

AnthropicCLAUDE.md

claude-quickstarts / mcp-server-typescript

anthropics/claude-quickstarts/managed-agents/mcp-server-typescript/CLAUDE.md

MCP server that exposes Managed Agents session primitives as tools. Two entrypoints sharing one tool set: src/server.ts (stdio → Claude Desktop and Claude Code) and src/server-http.ts (Streamable HTTP → claude.ai custom connector). This quickstart creates no agents, so there is no agents/ directory. It needs one environment, created once from environment.yaml (the command is in that file and in README.md). Commands: bun run stdio (Desktop, Code), bun run http (claude.ai), bun run typecheck.

No other project uses it yet

AnthropicCLAUDE.md

claude-quickstarts / roadtrip-planner

anthropics/claude-quickstarts/managed-agents/roadtrip-planner/CLAUDE.md

A Next.js chat built directly on a Managed Agent session: no chat framework, the event log is the app state. Teaches session event streaming (event_deltas), vault credential injection_location, per-session agent_with_overrides, and multiagent coordinator rosters. The planner calls the National Park Service and Windy APIs with keys it never holds, then hands its draft to a second agent for a quick critique. That second agent is an Opus reviewer running as a session thread. 1. Invoke /claude-api first. It loads the…

No other project uses it yet

LangChainCLAUDE.md

openwiki

langchain-ai/openwiki/CLAUDE.md

No summary in the file. Open it to read it.

NVIDIACLAUDE.md

TensorRT-LLM / agent-flow

NVIDIA/TensorRT-LLM/agent-flow/CLAUDE.md

No summary in the file. Open it to read it.

NVIDIACLAUDE.md

TensorRT-LLM

NVIDIA/TensorRT-LLM/CLAUDE.md

No summary in the file. Open it to read it.

ElasticCLAUDE.md

logstash

elastic/logstash/CLAUDE.md

See AGENTS.md.

Model Context ProtocolCLAUDE.md

typescript-sdk

modelcontextprotocol/typescript-sdk/CLAUDE.md

The principles this SDK is built and reviewed by. They are not a checklist: apply them with judgement. Style belongs to Prettier, ESLint and the compiler.

No other project uses it yet