Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/bluewings1211/codebase-rag/claude-mdgit clone --depth 1 https://github.com/bluewings1211/codebase-RAGWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01675 | $0.01675 |
| Opus 5 | $0.00838 | $0.00838 |
| Sonnet 5 | $0.00335 | $0.00335 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
codebase-RAG CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Development Commands
# Setup and Installation
./setup.sh # Run setup script
# Run MCP Server
uv run python src/run_mcp.py # Start MCP server
# Manual Indexing
uv run python manual_indexing.py -d "." -m clear_existing # Full reindex
uv run python manual_indexing.py -d "." -m incremental # Incremental update
# Testing
uv run pytest src/tests/ # Run tests
Architecture Overview
This is a Codebase RAG (Retrieval-Augmented Generation) MCP Server that enables AI agents to understand and query codebases using natural language with function-level precision through intelligent syntax-aware code chunking.
Project Structure
src/
├── main.py # MCP server entry point
├── run_mcp.py # Server startup script
├── models/ # Data models and structures
│ ├── code_chunk.py # Intelligent chunk representations
│ └── file_metadata.py # File tracking and metadata
├── services/ # Core business logic
│ ├── code_parser_service.py # AST parsing and chunking
│ ├── indexing_service.py # Orchestration and processing
│ ├── embedding_service.py # Ollama integration
│ ├── reranker_service.py # Cross-encoder reranking (Two-Stage RAG)
│ ├── qdrant_service.py # Vector database operations
│ └── project_analysis_service.py # Repository analysis
├── tools/ # MCP tool implementations
│ ├── core/ # Error handling and utilities
│ ├── indexing/ # Parsing and chunking tools
│ └── project/ # Project management tools
├── utils/ # Shared utilities
│ ├── logging_config.py # Centralized logging with file rotation
│ ├── language_registry.py # Language support definitions
│ ├── tree_sitter_manager.py # Parser management
│ └── performance_monitor.py # Progress tracking
└── prompts/ # Advanced query prompts (future)
Root Files:
├── manual_indexing.py # Standalone indexing tool
├── pyproject.toml # uv/Python configuration
└── docs/ # Documentation (referenced)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 160 lines · 1,675 tokens per session scan A 0604ba24f0fc
codebase-RAG CLAUDE.md is an instructions file published in the GitHub repository bluewings1211/codebase-RAG (15 stars, last pushed 8mo ago), licensed MIT. It adds 1,675 tokens to every session, about $0.0084 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
mcp-documentation-server copilot-instructions.md
Instructions for andrea9293/mcp-documentation-server, covering mcp documentation server - ai coding agent instructions, architecture overview, core components, server entry point (src/server.ts) and embedding providers (src/embedding-provider.ts).
notebooklm-skill copilot-instructions.md
Instructions for claude-world/notebooklm-skill: This Python project provides a JSON-first CLI, five async pipelines, and 13 MCP tools for NotebookLM. Keep all notebooklm-py API adaptation in scripts/common.py so the three public surfaces stay consistent. Follow the Ruff and mypy configuration, use typed async code…
rag-rat AGENTS.md
Instructions for cq27-dev/rag-rat, covering agents.md, prefer the rag-rat mcp for code browsing, record durable learnings as rag-rat memories, repo orientation and worktree correctness.
ai-agent-history-rag-mcp CLAUDE.md
Instructions for no13productions/ai-agent-history-rag-mcp, covering claude.md, knowledge source, project overview, tech stack and build and run commands.
quarry CLAUDE.md
Instructions for punt-labs/quarry, covering quarry, mandatory reading, architecture, how a query works and how ingestion works.
local_faiss_mcp CLAUDE.md
Instructions for nonatofabio/local_faiss_mcp, covering claude.md, project overview, architecture, key design principles and development commands.