nodeterm
eneskirca/nodeterm/CLAUDE.md
leaf, never a hop, so a CLI's own children (Codex's native `codex.exe`, MCP servers) cannot make the pane ambiguous. **A RELEASED session is still a messaging target.** Park
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.
eneskirca/nodeterm/CLAUDE.md
leaf, never a hop, so a CLI's own children (Codex's native `codex.exe`, MCP servers) cannot make the pane ambiguous. **A RELEASED session is still a messaging target.** Park
777genius/claude_agent_teams_ui/CLAUDE.md
editor** — edit files with Git support without leaving the app - **MCP integration** — built-in mcp-server for external tools and agent plugins - **Post-compact context recovery** — restores team-management instructions
1 project uses a version of this
0xMassi/webclaw/CLAUDE.md
Webclaw Rust workspace: CLI + MCP server for web content extraction into LLM-optimized formats. ## Architecture ``` webclaw/ crates/ webclaw-core/ # Pure extraction engine. WASM-safe. Zero network deps. # + ExtractionOptions (include/exclude
antonbabenko/terraform-skill/CLAUDE.md
from SKILL.md) — CI-owned, never hand-edit ├── mcp.json # Optional Kiro MCP (read-only terraform-mcp-server) ├── tests/ # Baseline scenarios and rationalization tracking │ ├── baseline-scenarios.md │ ├── compliance-verification.md │ └── rationalization-table.md └── .github/ ├── release/ │ ├── pre-commit.js # Release version
No other project uses it yet
afnanenayet/diffsitter/CLAUDE.md
grammar compilation cargo build --profile production # Release build with LTO + strip cargo build --features mcp-server --bin tree-sitter-mcp # MCP server binary # Test cargo nextest run --all-features
ddalcu/mlx-serve/app/CLAUDE.md
# Swift macOS app (MLX Core) — AI context Compressed rules. Full war stories: `../docs/gotchas/app.md`. Full
Steady9 mentions in 2 weeks
No other project uses it yet
AgentsMesh/AgentsMesh/CLAUDE.md
terminals (Pods) │ │ - Executes AI agents (Claude Code, Aider, etc.) │ │ - Streams terminal output back to server │ │ - Auto certificate renewal before expiry │ └─────────────────────────────────────────────────────────────┘ ``` ## Backend Structure ``` backend/ ├── cmd/server/ # Entry point ├── internal/ │ ├── api/rest/ # REST
HermannBjorgvin/Clawdmeter/desktop/CLAUDE.md
running: `claude -p --model haiku --output-format stream-json --verbose --no-session-persistence --strict-mcp-config --tools ""`, hooks and auto memory off, cwd = state dir. It reads the `rate_limit
Steady3 mentions in 2 weeks
No other project uses it yet
stacklok/toolhive/CLAUDE.md
Kubernetes operator (`thv-operator`), and a proxy runner (`thv-proxyrunner`) for container-based MCP server isolation. **To understand the system, start with the [Architecture Documentation](docs/arch/README.md).** Begin at the [Architecture
Steady14 mentions in 2 weeks
No other project uses it yet
lhfer/claude-howto-zh-cn/CLAUDE.md
名称 - skill / subagent / plugin 名称 - YAML frontmatter key - JSON / YAML key - CLI flags - 环境变量名 - MCP server 名 - 代码块里的可执行命令 ## 推荐提交流程 1. 改文档或示例 2. 跑 `uv run python scripts/validate_localization.py
jsverse/transloco/CLAUDE.md
exec nx test`) - avoids using globally installed CLI - You have access to the Nx MCP server and its tools, use them to help the user - For Nx plugin best practices
jhlee0409/claude-code-history-viewer/CLAUDE.md
type: "server_tool_use"`) - e.g., web_search - ✅ Web search results (`type: "web_search_tool_result"`) - ✅ Document content (`type: "document"`) - PDF and plain text - ✅ Search results (`type: "search_result"`) - ✅ MCP tool
anthropics/cwc-workshops/agent-battle/CLAUDE.md
point is for them to **learn how CMA's levers work** — system prompt, skills, MCP servers, model choice — not just to win. ## Be a facilitator, not an answer key - When
Kocoro-lab/Shannon/CLAUDE.md
pytest ``` ## Project Structure - **`rust/agent-core/`**: Enforcement gateway, WASI sandbox, gRPC server - **`go/orchestrator/`**: Temporal workflows, budget manager, complexity analyzer - **`python/llm-service/`**: LLM providers, MCP tools, agent loop - **`protos/`**: Shared protocol buffer definitions - **`deploy/compose
tractorjuice/arc-kit/CLAUDE.md
Agent Skills (`skills/ /SKILL.md`) invoked with `/skill:arckit- `; the `kimi.plugin.json` manifest carries the six MCP servers and auto-loads `architecture-workflow` at session start. The CLI and plugin have independent
Steady8 mentions in 2 weeks
No other project uses it yet
XRPLF/xrpl-dev-portal/.claude/CLAUDE.md
date XRPL protocol, API, or SDK info, use the `xrpl-docs` MCP server. Prefer this over web search or memory when writing code samples, documenting protocol behavior, or answering
apconw/Aix-DB/CLAUDE.md
stream end) - **Datasource support**: MySQL, PostgreSQL, Oracle, SQL Server, ClickHouse, DM, Doris, StarRocks (via SQLAlchemy or native drivers) - **MCP integration**: External mcp-hub service, configured via `MCP_HUB_COMMON
postalsys/emailengine/CLAUDE.md
SMTP server's authentication switch, the TLS provisioning mode and hostname list, the service URL, mail certificate checking, the URL the AI key is sent to, the MCP and audit
AmoyLab/Unla/CLAUDE.md
acts as a lightweight proxy and management layer that converts existing APIs and MCP servers into MCP-compliant services through configuration-driven approaches. **Key Architecture:** - **Control Plane**: `cmd/apiserver` - REST
atomicmemory/llm-wiki-compiler/docs/CLAUDE.md
Pages are MDX files with YAML frontmatter - Configuration lives in `docs.json` - Use the Mintlify MCP server, `https://mcp.mintlify.com`, to edit content and settings via MCP - Use the Mintlify docs MCP
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.