What is CodeRAG CLAUDE.md?

Project instructions for CodeRAG, a tool that builds a searchable map of a codebase and related documents for AI coding agents. It uses source code, documentation, and project backlog information to provide context through MCP tools.

Helping an AI agent understand, search, and navigate the CodeRAG project, including its ingestion pipeline, storage, retrieval engine, MCP server, and tests.

AI agents often lack enough context about a large or unfamiliar codebase. These instructions explain the project’s structure, technology choices, and context-retrieval system so agents can work with it more accurately.

How maciek-O-digiaidev/CodeRAG configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to maciek-O-digiaidev/CodeRAG. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/maciek-O-digiaidev/CodeRAG/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/maciek-O-digiaidev/CodeRAG

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/maciek-o-digiaidev/coderag/claude-md/github.svg)](https://agentmods.dev/instructions/maciek-o-digiaidev/coderag/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/maciek-o-digiaidev/coderag/claude-md"><img src="https://agentmods.dev/badge/instructions/maciek-o-digiaidev/coderag/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/maciek-o-digiaidev/coderag/claude-md"><img src="https://agentmods.dev/badge/instructions/maciek-o-digiaidev/coderag/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,123 This file is loaded in full into every session.

When invoked 1,123 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What 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 5.1	$0.01123	$0.01123
Opus 5.5	$0.00449	$0.00449
Sonnet 5.5	$0.00225	$0.00225
Haiku 4.5	$0.00112	$0.00112

Measured 2mo ago against content hash 8e808069fb01, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

CodeRAG 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 2mo 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.

CLAUDE.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeRAG — Project Context for AI Agents

What is CodeRAG?

CodeRAG is an intelligent codebase context engine for AI coding agents. It creates a semantic vector database (RAG) from source code, documentation, and project backlog, then exposes it as MCP tools that give AI agents deep understanding of the entire codebase.

Architecture

Sources (Git, Jira, Confluence, MD)
  → Ingestion Pipeline (Tree-sitter AST, NL enrichment, metadata)
    → Embedding & Storage (LanceDB, BM25 index, dependency graph)
      → Retrieval Engine (hybrid search, graph expansion, re-ranking, token budget)
        → Agent Interface (MCP Server: coderag_search, coderag_context, coderag_status)

Tech Stack

Language: TypeScript (Node.js, ESM)
Code parsing: Tree-sitter (WASM bindings)
Embedding (local): Ollama + nomic-embed-text
Embedding (API): voyage-code-3, OpenAI text-embedding-3-small
Vector DB: LanceDB (embedded, zero-infra)
Keyword search: MiniSearch (BM25)
NL Summarization: Ollama (qwen2.5-coder / llama3.2)
MCP Server: @modelcontextprotocol/sdk
CLI: Commander.js
Testing: Vitest with coverage
Package manager: pnpm workspaces

Project Structure

coderag/
├── packages/
│   ├── core/              # Core library: ingestion, embedding, retrieval
│   │   ├── src/
│   │   │   ├── ingestion/  # Tree-sitter parser, chunking, NL enrichment
│   │   │   ├── embedding/  # Provider abstraction, LanceDB, BM25
│   │   │   ├── retrieval/  # Hybrid search, graph expansion, context assembly
│   │   │   ├── config/     # .coderag.yaml parser
│   │   │   └── types/      # Shared TypeScript types
│   │   └── tests/
│   ├── cli/               # CLI tool (coderag init/index/search/serve/status)
│   │   ├── src/
│   │   └── tests/
│   ├── mcp-server/        # MCP server (stdio + SSE transport)
│   │   ├── src/
│   │   └── tests/
│   └── benchmarks/        # Benchmark suite
│       ├── datasets/
│       └── src/
├── .coderag.yaml          # Project config (dogfooding!)
├── CLAUDE.md              # This file
├── pnpm-workspace.yaml
└── tsconfig.base.json

Read the full file on GitHub · 87 lines

Changes

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.

2mo ago First seen · 87 lines · 1,123 tokens per session scan A 8e808069fb01

Subscribe to this mod's changes

CodeRAG CLAUDE.md is an instructions file published in the GitHub repository maciek-O-digiaidev/CodeRAG (5 stars, last pushed 8mo ago), licensed MIT. It adds 1,123 tokens to every session, about $0.0045 per session on Opus 5.5. 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 2026-08-31.

Data and AI RAG and vectors ai-coding codebase-search developer-tools lancedb mcp ollama

CodeRAG CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
CodeRAG CLAUDE.mdmaciek-O-digiaidev/CodeRAG	Instructions file	5	8mo ago	MIT	A	1,123	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

CodeRAG: Instructions file for Claude Code