agent-brain-multi

A search command for Agent Brain that combines keyword matching, meaning-based search, and connections between related information. It merges results from these search methods into one ranked list.

In plain words
What is it for?
Use it to investigate implementation details, search documentation and code together, filter results by source or language, and inspect relevance scores.
Why use it?
It helps when a question uses unfamiliar wording, requires broad coverage, or depends on relationships between documents and code.

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-multi
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,878 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 $0.00015 $0.01878
Opus 5 $0.00008 $0.00939
Sonnet 5 $0.00003 $0.00376
Haiku 4.5 $0.00002 $0.00188

Measured 2d ago against content hash 8a4dd51e26b7, 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-multi 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-multi.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Performs multi-mode fusion search combining BM25 keyword matching, semantic vector search, and GraphRAG relationships using Reciprocal Rank Fusion (RRF). This is the most comprehensive search mode, finding results from all angles.

Multi-mode search is ideal for:

  • Complex queries requiring comprehensive results
  • When you want both content matches AND relationships
  • Investigating full implementation details
  • Combining technical terms with conceptual understanding
  • When you're not sure which mode would be best

Usage

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

Parameters

Parameter Required Default Description
query Yes - The comprehensive search query
--top-k, -k No 5 Number of results (1-20)
--threshold, -t No 0.3 Minimum relevance score (0.0-1.0)
--source-types No - Filter by source type (doc,code,test)
--languages No - Filter by programming language
--file-paths No - Filter by file path patterns (wildcards)
--scores No false Show individual vector/BM25 scores
--full No false Show full text content
--json No false Output as JSON
--url No from config Server URL (env: AGENT_BRAIN_URL)

How Multi-Mode Works

  1. BM25 Search: Finds exact term matches
  2. Vector Search: Finds semantically similar content
  3. Graph Search: Finds related entities and relationships
  4. RRF Fusion: Combines results using Reciprocal Rank Fusion
RRF_score(d) = Σ 1/(k + rank_i(d))

Where k is a constant (typically 60) and rank_i(d) is the rank of document d in result list i.

Execution

Pre-flight Check

# Verify server is running and capabilities
agent-brain status

Multi-mode works best with all indices available:

  • BM25 index: Built during indexing
  • Vector index: Requires embedding provider
  • Graph index: Requires ENABLE_GRAPH_INDEX=true

Read the full file on GitHub · 277 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 · 277 lines · 15 tokens per session scan A 8a4dd51e26b7

Subscribe to this mod's changes

agent-brain-multi is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,878 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.