codebase-graph CLAUDE.md

Instructions for CodeGraph, a system that maps a codebase into a searchable graph of code and related knowledge. It covers setup, code search, context retrieval, repository analysis, knowledge management, and graph queries.

In plain words
What is it for?
Use it to search a codebase, inspect its structure, retrieve related knowledge, manage graph entries, and run raw graph queries.
Why use it?
It gives an AI assistant a defined way to check whether a project is indexed, configure it, reindex it, and retrieve relevant code context.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/phoenixrr2113/codebase-graph/claude-md
Clone the repo
git clone --depth 1 https://github.com/Phoenixrr2113/codebase-graph
Per session 3,376 This file is loaded in full into every session.
When invoked 3,376 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.03376 $0.03376
Opus 5 $0.01688 $0.01688
Sonnet 5 $0.00675 $0.00675
Haiku 4.5 $0.00338 $0.00338

Measured 2d ago against content hash a75f37c49c11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-graph 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.

CLAUDE.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeGraph: AI Assistant Skill Document

CodeGraph indexes codebases into a graph database (FalkorDB) and provides MCP tools for code search, context retrieval, repository analysis, knowledge management, and raw graph queries.

Quick Start

Check if a codebase is indexed:

codebase({ action: "status" })

On a fresh install this returns configured: false and setupRequired: true. An empty database is valid and ready for setup.

If no projects are configured, save an absolute project path and then index it:

codebase({ action: "configure", projectAction: "set", projects: ["/path/to/project"] })
codebase({ action: "reindex", mode: "full", scope: "/path/to/project" })

Configuration does not index the project. Reindexing parses structure first and finishes embeddings. With no provider or provider key set, local nomic-ai/nomic-embed-text-v1.5 embeddings are the default. The first use downloads approximately 132 MiB and reports progress.

Tool Reference (5 tool groups, 25 actions)

1. search: Find code and knowledge

Vector search with optional cross-encoder reranking when a supported provider key is configured. Without one, search keeps vector-search ordering. Local 768-dimension embeddings remain the no-key default. Results include complexity, callers, callees, importerCount, and linkedKnowledge.

Action Use When Required Params
find Looking for files, functions, classes, symbols query
context Need relationships and structure for a file or symbol file or symbol

Search modes: searchScope: 'code' (default), 'knowledge', 'all' (RRF fusion).

Examples:

search({ action: "find", query: "parseProject" })
search({ action: "find", query: "authentication", searchScope: "all" })
search({ action: "context", file: "src/service.ts", includeRelationships: true })
search({ action: "context", symbol: "enrichedSearchV2" })

Multi-step questions: for complex queries that need iterative refinement, chain search calls in your agent. Examine results, refine the query, and search again. CodeGraph stays focused on per-call retrieval quality; orchestration is the agent's job.

Read the full file on GitHub · 205 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.

  1. 2d ago First seen · 205 lines · 3,376 tokens per session scan A a75f37c49c11

Subscribe to this mod's changes

codebase-graph CLAUDE.md is an instructions file published in the GitHub repository Phoenixrr2113/codebase-graph (7 stars, last pushed 8d ago), licensed MIT. It adds 3,376 tokens to every session, about $0.0169 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 2026-08-31.