agent-brain-graph

A code search command that follows relationships between functions, classes, and modules. GraphRAG combines a searchable relationship graph with retrieval to answer dependency and data-flow questions.

In plain words
What is it for?
Use it to find callers of a function, inspect class inheritance, explore module dependencies, and trace data flow after graph indexing is enabled.
Why use it?
Exact-word search may find a name but not explain how code connects; this is intended for tracing those connections.

Command

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 commands/spillwavesolutions/agent-brain/agent-brain-graph
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,648 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00016 $0.01648
Opus 5 $0.00008 $0.00824
Sonnet 5 $0.00003 $0.00330
Haiku 4.5 $0.00002 $0.00165

Measured 2d ago against content hash e9874e0f6a1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-brain-graph 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.

agent-brain-plugin/commands/agent-brain-graph.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Performs GraphRAG-powered search for relationship and dependency queries. This mode queries the knowledge graph to find entities (functions, classes, modules) and their relationships (calls, imports, inherits).

Graph search is ideal for:

  • Finding what calls a specific function
  • Exploring class inheritance hierarchies
  • Understanding module dependencies
  • Tracing data flow through code

Usage

/agent-brain:agent-brain-graph <query> [--top-k <n>] [--threshold <t>]

Parameters

Parameter Required Default Description
query Yes - The relationship or dependency query
--top-k No 5 Number of results (1-20)
--threshold No 0.3 Minimum similarity threshold (0.0-1.0)

Prerequisites

GraphRAG must be enabled before using graph search:

# Enable graph indexing
export ENABLE_GRAPH_INDEX=true
export GRAPH_STORE_TYPE=simple       # or kuzu
export GRAPH_USE_CODE_METADATA=true
export GRAPH_USE_LLM_EXTRACTION=true

# Optional dependencies
pip install "agent-brain-rag[graphrag]"          # LLM extractor
pip install "agent-brain-rag[graphrag-kuzu]"     # Kuzu backend

# Start server
agent-brain start

# Rebuild index with graph extraction
agent-brain index /path/to/code --rebuild

Check Graph Status

agent-brain status
# Look for: Graph Index: enabled (X entities, Y relationships)

Backend Requirements

Graph search is only available when using the ChromaDB storage backend (default). If you are using the PostgreSQL backend (AGENT_BRAIN_STORAGE_BACKEND=postgres), graph queries will return an error:

Error: Graph queries (mode='graph') require ChromaDB backend.
Current backend: 'postgres'.
To use graph queries, set AGENT_BRAIN_STORAGE_BACKEND=chroma.

To use graph search, switch to ChromaDB backend or use /agent-brain:agent-brain-hybrid for hybrid BM25 + vector search on any backend.

Execution

Read the full file on GitHub · 259 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 · 259 lines · 16 tokens per session scan A e9874e0f6a1c

Subscribe to this mod's changes

agent-brain-graph is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 1,648 once invoked, about $0.0001 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.