raptor
gadievron/raptor/CLAUDE.md
full list. 3. If the `sage_inception` tool is present in your available MCP tools, load `core/sage/CLAUDE.md` (persistent-memory workflow). If absent, SAGE is not installed — skip silently
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
gadievron/raptor/CLAUDE.md
full list. 3. If the `sage_inception` tool is present in your available MCP tools, load `core/sage/CLAUDE.md` (persistent-memory workflow). If absent, SAGE is not installed — skip silently
thevangelist/dembrandt/CLAUDE.md
frameworks, logoInstances, manifest, siteName } ``` ## Dependencies - `playwright-core` — browser automation (browsers install separately) - `@modelcontextprotocol/sdk`, `zod` — MCP server; both must stay regular dependencies, optional peers broke `npx` installs - `chalk` — terminal colors - `commander
simonlin1212/TradingAgents-astock/CLAUDE.md
一路污染记忆日志与绩效统计。 ### 探测 mootdx 不能覆写用户配置(v0.5.10,v0.5.12 重构) `StdQuotes.__init__` 里有 `config.set('BESTIP', {'HQ': self.server})`——**每建一次带 `server` 的 client 都会持久化写进 mootdx 配置文件**。逐台探测会把用户原本配好的服务器 一路覆写,最后留下一台死的,还会连累同机其它用 mootdx 的程序。 用 `with _preserve_mootdx
samber/cc-skills-golang/CLAUDE.md
list based on the skill's purpose. **Qualify MCP tool names with their server.** The `mcp__context7__query-docs` form above is Claude Code's; other harnesses expect `ServerName:tool
No other project uses it yet
bytebase/dbhub/CLAUDE.md
this repository. # DBHub Development Guidelines DBHub is a zero-dependency, token efficient database MCP server implementing the Model Context Protocol (MCP) server interface. This lightweight server bridges MCP-compatible clients
dathere/qsv/.claude/skills/CLAUDE.md
claude/skills/.claude-plugin/plugin.json` carries the plugin manifest (name, version, author, keywords) but does NOT embed an MCP-server config or set `QSV_MCP_EXPOSE_ALL_TOOLS`. The MCP server starts
Steady7 mentions in 2 weeks
No other project uses it yet
mckinsey/vizro/CLAUDE.md
Vizro dashboard framework - `vizro-ai/`: Framework for AI-assisted dashboard development - `vizro-mcp/`: Model Context Protocol server for AI-assisted dashboard development - `vizro-dash-components/`: Custom Dash components maintained
No other project uses it yet
strukto-ai/mirage/CLAUDE.md
Test: `uv run pytest`. - TypeScript lives in `typescript/` (`packages/core`, `node`, `browser`, `cli`, `server`, `agents`, `dsh`, `opencode`): `pnpm install`, `pnpm build`, `pnpm typecheck`, `pnpm test`. Rebuild the dists after a merge
nextlevelbuilder/goclaw/CLAUDE.md
gating ├── eventbus/ Domain event bus with worker pool, dedup, retry (v3) ├── gateway/ WS + HTTP server, client, method router │ └── methods/ RPC handlers (chat, agents, sessions, config, skills, cron, pairing) ├── hooks/ Hook
p-org/P/CLAUDE.md
Core logic including different interaction modes - `src/ui/`: User interface components (Streamlit web app, CLI, MCP server) - `src/utils/`: Utilities for code generation, compilation, and P language analysis - `resources/`: Context files, examples
AIDotNet/OpenDeepWiki/CLAUDE.md
this repository. ## Key Docs to Read - `README.md` for Docker/Makefile workflows, environment variables, and MCP setup. - `.github/copilot-instructions.md` for architecture notes and development commands. ## Common Commands ### Backend (.NET) - Build solution: `dotnet build
RunMaestro/Maestro/CLAUDE.md
# CLAUDE.md Essential guidance for working with this codebase. For detailed architecture, see [ARCHITECTURE.md](ARCHITECTURE.md
pedramamini/Maestro/CLAUDE.md
# CLAUDE.md Essential guidance for working with this codebase. For detailed architecture, see [ARCHITECTURE.md](ARCHITECTURE.md
chrisvel/tududi/CLAUDE.md
briefs - Caching strategy and API endpoints - Adding new AI features 23. **[MCP Integration](docs/14-mcp-integration.md)** - Model Context Protocol server for AI tool integration - 65 tools across tasks, comments, projects, areas, goals
Steady35 mentions in 2 weeks
No other project uses it yet
awslabs/agentcore-samples/01-features/02-host-your-agent/01-runtime/04-coding-agents/03-code-agents-competition-e2e/coding_agents/claude-code/CLAUDE.md
reading issues, applying fixes, and submitting PRs. ## MCP Tools You have a `gateway` MCP server connected that provides GitHub tools (prefixed `mcp__gateway__GitHubMCP___`). Use them directly — no manual HTTP
punitarani/fli/CLAUDE.md
interface** (`fli/cli/`) - Typer-based command line tool with `flights` and `dates` commands - **MCP server** (`fli/mcp/`) - Model Context Protocol server for AI assistant integration - **Core utilities** (`fli/core/`) - Shared parsing and building
hi-godot/godot-ai/.claude/CLAUDE.md
calls for it: | Task | Read | |---|---| | Adding or changing an MCP tool | [docs/tool-surface.md](../docs/tool-surface.md) | | Verifying a change before commit | [docs/verification.md](../docs/verification.md) | | Server start/adopt/teardown, reload | [docs/server-lifecycle.md](../docs/server-lifecycle.md) | | Cutting a release | [docs/releasing.md](../docs/releasing.md
Intelligent-Internet/ii-agent/CLAUDE.md
Socket.IO command handlers (21 total) │ └── pubsub/ # Async pub/sub (SioCallback + DatabaseCallback) │ ├── settings/ # Admin/user settings (LLM, MCP, skills) │ └── workers/ # Background jobs ├── celery/ # Celery task definitions & decorators └── cron/ # Scheduled jobs (credit refresh, sandbox
giancarloerra/SocratiCode/CLAUDE.md
query. > **Keep the connection alive during indexing.** Indexing runs in the background — the MCP server continues working even when not actively responding to tool calls. However, some MCP hosts
Steady3 mentions in 2 weeks
No other project uses it yet
ResearAI/DeepScientist/CLAUDE.md
structured artifacts - `memory/` - Global and quest-scoped memory - `bash_exec/` - Managed shell sessions - `mcp/` - MCP server implementation - `runners/` - Runner implementations (Codex, Claude, OpenCode) - `bridges/` - Connector transport adaptation - `channels/` - Connector delivery
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.