daScript
GaijinEntertainment/daScript/CLAUDE.md
CMake, Python tooling). **Cross-tree guard:** MCP results and LSP diagnostics prepend a `CROSS-TREE WARNING` when you query a file **outside the server's own tree** - that answer used
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.
GaijinEntertainment/daScript/CLAUDE.md
CMake, Python tooling). **Cross-tree guard:** MCP results and LSP diagnostics prepend a `CROSS-TREE WARNING` when you query a file **outside the server's own tree** - that answer used
GaijinEntertainment/daScript/install/CLAUDE.md
modules/ /`; lock file `daspkg.lock`. Full flags and the `.das_package` manifest format: `skills/daspkg.md`. ## MCP Server (AI Tool Integration) `utils/mcp/` is a [Model Context Protocol](https://modelcontextprotocol.io/) server exposing compiler
fcakyon/claude-codex-settings/CLAUDE.md
Plugins under `plugins/` support Claude Code, Codex CLI, and Cursor; plugins with skills or MCP servers also support Antigravity CLI. ## Repo Structure ``` claude-settings/ CLAUDE.md # this file (repo dev guide
No other project uses it yet
chernistry/bernstein/CLAUDE.md
system (pluggy) - `src/bernstein/plugins/` | | `tui/` | Textual TUI - `src/bernstein/tui/` | | `github_app/` | GitHub App integration - `src/bernstein/github_app/` | | `mcp/` | MCP server - `src/bernstein/mcp/` | | `benchmark/` | SWE-bench - `src/bernstein/benchmark/` | ## Directory context files Per-directory context files for agents
1 project uses a version of this
Shpigford/clearly/CLAUDE.md
previewing markdown files in Finder. There is intentionally **no** vault index, sync, AI, MCP server, sidebar, wiki-links, tags, backlinks, or command palette. If you're tempted to add infrastructure
openfootmanager/openfootmanager/src/CLAUDE.md
does **not** reach text whose only reader is an AI agent or a modder — MCP tool output, `ofm-cli`, `docs/` — which stays English on purpose; the root [`../CLAUDE.md`](../CLAUDE.md) rule
openfootmanager/openfootmanager/src-tauri/CLAUDE.md
registered in the builder in `src/lib.rs`. Multi-step orchestration sits in `src/application/`. The MCP server (`src/mcp_server/`, behind the `mcp` Cargo feature) exposes the same behaviour to AI agents. It calls
akii09/pdfx/CLAUDE.md
into the user's project. ## Architecture ``` apps/www → Documentation site + registry server (Next.js) packages/cli → CLI / MCP server (pdfx-cli on npm) packages/shared → Cross-package types & schemas (Zod) ``` The registry lives
affaan-m/agentshield/CLAUDE.md
AgentShield Security auditor for AI agent configurations (Claude Code, MCP servers, hooks, agents). ## Build & Test ```bash npm run build # tsc + tsup → dist/ npm test # vitest (912 tests
platonai/Browser4/CLAUDE.md
Project Context for Claude ## Architecture ``` browser4-cli (Rust) ──MCP over HTTP──▶ browser4-rest (Kotlin/Spring) ──▶ PulsarWebDriver (Kotlin/CDP) ▲ │ │ ▼ └──── e2e tests ────▶ Fixture HTTP server (Rust test harness) ``` - **CLI:** `cli/browser4-cli/` — Rust binary, talks
obot-platform/obot/CLAUDE.md
Obot is an open source AI governance platform with the following features: - MCP registry - MCP server hosting and management - LLM gateway and audit logs - Agent Skills registry - Device Management
obot-platform/obot/docs/CLAUDE.md
relative path to the markdown file, and keep the `.md` extension. ```markdown [MCP Servers](./mcp-servers.md) [User Roles](../configuration/user-roles.md) [Auditor Role](../configuration/user-roles.md#auditor) ``` Never write the link as a site path
No other project uses it yet
hoangsonww/Claude-Code-Agent-Monitor/CLAUDE.md
printed command, surfaced in the UI and by `ccam update-check`.) - `mcp/`: local MCP server exposing dashboard operations as tools. - `cli/`: the `ccam` CLI (Commander.js command tree; `bin/ccam.js
cookjohn/zotero-mcp/zotero-mcp-plugin/CLAUDE.md
Zotero MCP Plugin ## Project Overview A Zotero plugin that provides MCP (Model Context Protocol) server functionality, enabling AI assistants to interact with Zotero's library data. ## Tech Stack - TypeScript - Zotero
whisper-money/whisper-money/CLAUDE.md
rather than explaining obvious details. === boost rules === # Laravel Boost ## Tools - Laravel Boost is an MCP server with tools designed specifically for this application. Prefer Boost tools over manual alternatives like
vndee/llm-sandbox/CLAUDE.md
policies and pattern matching - Code scanning for vulnerabilities - Resource limits and network isolation 6. **MCP Server** (`llm_sandbox/mcp_server/`) - Model Context Protocol integration - Enables Claude Desktop and other MCP clients
No other project uses it yet
Leezekun/MassGen/CLAUDE.md
converted to Python wrapper scripts that agents call via filesystem execution — **unless** the MCP server name is in `FRAMEWORK_MCPS` (`massgen/filesystem_manager/_constants.py`). Framework MCPs stay as direct protocol tools sent
AgriciDaniel/banana-claude/CLAUDE.md
plugin-dir . plugin details banana-claude@inline` to confirm the expected skill, agents, and MCP server when Claude Code is present. Live acceptance is a separate manual gate using
No other project uses it yet
localgpt-app/localgpt/CLAUDE.md
while one has the world open cargo run -- world mcp # the shim: a stdio MCP server over an app's open canvas # Test cargo test --workspace # All tests cargo test
yuanchenglu/claude-code-webui/CLAUDE.md
Backend passes `session_id` to SDK via `options.resume` ## MCP Integration (Model Context Protocol) Playwright MCP server integration for automated browser testing and demo verification. ### Configuration ```json { "mcpServers": { "playwright": { "type": "stdio
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.