How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
JNTMTMTMCLAUDE.mdJNTMTMTM/eIsland/.claude/CLAUDE.md
BEFORE grep/find or reading files when you need to understand or locate code: - **MCP tool** (when available): `codegraph_explore` answers most code questions in one call — the relevant symbols' verbatim
sepivipCLAUDE.mdsepivip/SeekerClaw/CLAUDE.md
Model list can be updated via app update or future remote config. ## MCP Servers (Remote Tools) Users can add remote MCP (Model Context Protocol) servers in Settings > MCP Servers. Each
gendigitalincCLAUDE.mdgendigitalinc/sage/CLAUDE.md
loader/sanitizer + `mergeExtendedInfo` helper - `product-version.ts` — Platform-agnostic `product.json` version reader used by hook runner and MCP server child processes 4. **Plugin Config** — `hooks/hooks.json` registers hooks, `.claude-plugin/plugin.json` is the plugin
nirholasCLAUDE.mdnirholas/cryptocurrency.cv/CLAUDE.md
RSS/Atom feeds, JSON REST API, historical archive with market context, embeddable widgets, ChatGPT plugin, MCP server (hosted at https://cryptocurrency.cv/api/mcp, local via `npx -y @nirholas/free-crypto-news-mcp`, source in mcp
clay-goodCLAUDE.mdclay-good/OpenLore/CLAUDE.md
gold This project uses OpenLore for persistent architectural memory. Call `orient " "` (via the openlore MCP server, or `npx openlore orient --json`) **before touching a module you have not yet read
ucsandmanCLAUDE.mducsandman/DashClaw/CLAUDE.md
rename `.jsx`↔`.js`** (e.g. keep `app/connect/page.jsx`). It churns diffs for zero behavior change. - **DashClaw MCP server needs only `DASHCLAW_URL` + `DASHCLAW_API_KEY`** (optionally `DASHCLAW_AGENT
FradSerCLAUDE.mdFradSer/mcp-server-mas-sequential-thinking/CLAUDE.md
Essential Commands ```bash # Setup & Development uv pip install -e ".[dev]" # Install dependencies uv run mcp-server-mas-sequential-thinking # Run server uv run ruff check . --fix && uv run ruff format
AnttiHeroCLAUDE.mdAnttiHero/lavern/CLAUDE.md
agent definitions - `src/agents/profiles.ts` — 63-agent profile registry (skill ratings, personality, DiceBear avatars) - `src/mcp/tools/` — 21 MCP tool modules (debate board, scoring, verification, memory, risk pricing, baselines, knowledge base, report cards, quality
Prorise-coolCLAUDE.mdProrise-cool/Claude-Code-Multi-Agent/CLAUDE.md
预测性调度**。 ### 1. 工具能力映射表 (Intent-Capability Mapping) * **需要理解复杂代码/依赖** ➔ 必须调用 `context7-mcp` (架构分析) 或 `everything-search` (定位)。 * **需要深度逻辑/根因分析** ➔ 必须激活 `server-sequential-thinking` (链式推理)。 * **需要外部知识/文档** ➔ 调用 `Exa AI` (搜索
sleuth-ioCLAUDE.mdsleuth-io/sx/CLAUDE.md
event format - [Metadata Spec](docs/metadata-spec.md) - Asset metadata format and fields - [MCP Spec](docs/mcp-spec.md) - MCP server tools (query) - [Environment Variables](docs/environment-variables.md) - SX_CONFIG_DIR, SX_CACHE_DIR, and isolation recipes - [GitHub
theexperiencecompanyCLAUDE.mdtheexperiencecompany/gaia/CLAUDE.md
Executor agent** (worker tier, all tools) → same file (`build_executor_*`) + `apps/api/app/agents/tools/executor_tool.py` - **Subagents** (per-user MCP workers + spawned isolation) → `apps/api/app/agents/core/subagents/` + `apps/api/app/config/oauth_config.py` - **Bots** → `apps/bots/{telegram,whatsapp,discord,slack}/` + `libs/shared/ts/src/bots/` - **Voice** → `apps/voice-agent/src/worker.py` - **Skills
willibrandonCLAUDE.mdwillibrandon/pixel-plugin/CLAUDE.md
pixel-plugin **Version:** 0.1.0 **Type:** Claude Code Plugin (Skills + Commands + MCP Integration) **Dependencies:** pixel-mcp server (Go binary), Aseprite v1.3.0+ ## Architecture The plugin follows a layered architecture: 1. **User Layer
Othmane-KhadriCLAUDE.mdOthmane-Khadri/YALC-the-GTM-operating-system/CLAUDE.md
www.lemlist.com/claude-skills) under `.claude/skills/lemlist/`, plus a flagship orchestration skill at `.claude/skills/lemlist-campaign-from-icp/` and a lemlist MCP server pre-declared in `.mcp.json`. Together they cover the full outbound loop inside Claude Code
zenml-ioCLAUDE.mdzenml-io/kitaru/docker/CLAUDE.md
dev-worker.Dockerfile` | Development worker | Local repository source | | `release-client.Dockerfile` | Release client | Published PyPI wheel | | `release-server.Dockerfile` | Release server | Published PyPI wheel | | `release-worker.Dockerfile` | Release worker | Published PyPI wheel | | `onboarding-sandbox.Dockerfile` | Onboarding sandbox | Published worker image
zenml-ioCLAUDE.mdzenml-io/kitaru/docs/CLAUDE.md
schema-check` and describe the tools present in the current snapshot. The native v2 MCP server does not expose stack or model-alias management
plur-aiCLAUDE.mdplur-ai/plur/CLAUDE.md
plur-ai/core — engram engine (learn, recall, inject, search, decay, sync) @plur-ai/mcp — MCP server (Claude Code, Cursor, Windsurf) @plur-ai/claw — OpenClaw ContextEngine plugin @plur-ai/opencode — opencode
xiaotonngCLAUDE.mdxiaotonng/pikiloom/CLAUDE.md
proxy. Providers + Profiles vault injects credentials per agent at spawn time. 4. **Tool** — Skills, MCP servers, CLI tools, merged across global / workspace scopes. The orchestrator is the product. Lead with
vizra-aiCLAUDE.mdvizra-ai/vizra-adk/CLAUDE.md
traces php artisan vizra:trace:cleanup # Manage prompt versions php artisan vizra:prompts # MCP server management php artisan vizra:mcp:list # Vector memory operations php artisan vizra:vector:store --file
HarmonicSecurityCLAUDE.mdHarmonicSecurity/claudit-sec/CLAUDE.md
Settings | `claude_desktop_config.json` → preferences | keepAwakeEnabled, allowAllBrowserActions, menuBar, sidebar | | Cowork Settings | `cowork_settings.json`, `config.json` | scheduledTasks, webSearch, networkMode | | MCP Servers | `claude_desktop_config.json` → mcpServers | Server names, commands, env var keys | | Plugins | `installed_plugins.json`, remote manifest, marketplace cache
varun29ankuSCLAUDE.mdvarun29ankuS/shodh-memory/CLAUDE.md
this codebase ## Codebase Map - `src/` — Rust core (memory, API server, embeddings, graph, vector search) - `mcp-server/` — TypeScript MCP server (45 tools, index.ts) - `tui/` — Rust TUI dashboard - `hooks/` — Claude Code hooks
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.
