agent-brain-bm25

agent-brain-bm25 is a command for coding agents from SpillwaveSolutions/agent-brain. It costs 16 tokens per session (1,412 once invoked), scanned A, original, MIT.

A command that searches indexed content by matching exact words and identifiers. BM25 is a keyword-ranking method, so it is suited to names, error messages, configuration keys, and code symbols.

In plain words
What is it for?
Use it to find error codes, function or class names, variable names, configuration keys, and stack-trace text.
Why use it?
It avoids relying on a meaning-based search service when you already know the exact term and need a fast, offline lookup.

Command

Part of the agent-brain-plugin plugin — 29 commands, 3 agents shipped together

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-bm25
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain

Or install agent-brain-plugin, the plugin that ships this one along with the rest of its 29 commands, 3 agents.

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.

agentmods badge for agent-brain-bm25

README.md
[![agentmods](https://agentmods.dev/badge/commands/spillwavesolutions/agent-brain/agent-brain-bm25.svg)](https://agentmods.dev/commands/spillwavesolutions/agent-brain/agent-brain-bm25)
Your own site
<a href="https://agentmods.dev/commands/spillwavesolutions/agent-brain/agent-brain-bm25"><img src="https://agentmods.dev/badge/commands/spillwavesolutions/agent-brain/agent-brain-bm25.svg" alt="Measured on agentmods" height="20"></a>
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 1,412 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 $0.01412
Opus 5 $0.00008 $0.00706
Sonnet 5 $0.00003 $0.00282
Haiku 4.5 $0.00002 $0.00141

Measured 4d ago against content hash ef4d38f81b15, 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-bm25 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 4d 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-bm25.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Performs BM25 (Best Matching 25) keyword search for fast, exact term matching. This mode is optimized for technical queries where you know the exact terms you're looking for.

BM25 search is ideal for:

  • Error messages and codes
  • Function and class names
  • Configuration keys and variables
  • Technical identifiers
  • When speed is critical (10-50ms response)
  • Offline searching (no API calls)

Usage

/agent-brain:agent-brain-bm25 <query> [--top-k <n>]

Parameters

Parameter Required Default Description
query Yes - The exact search terms
--top-k No 5 Number of results (1-20)

When to Use BM25 vs Other Modes

Use BM25 Use Semantic/Hybrid Instead
"AuthenticationError" "how does auth work"
"recursiveCharacterTextSplitter" "text splitting strategies"
"OPENAI_API_KEY" "API configuration"
"def process_document" "document processing flow"
error codes, stack traces conceptual explanations
exact function names "functions that do X"

Execution

Pre-flight Check

# Verify server is running
agent-brain status

If not running:

agent-brain start

Search Command

agent-brain query "<query>" --mode bm25 --top-k <k>

Examples

# Search for error message
agent-brain query "ConnectionRefusedError" --mode bm25

# Search for function name
agent-brain query "process_document" --mode bm25

# Search for configuration key
agent-brain query "EMBEDDING_MODEL" --mode bm25

# More results
agent-brain query "AuthenticationError" --mode bm25 --top-k 10

# Multiple terms (finds documents with all terms)
agent-brain query "OAuth client_id redirect_uri" --mode bm25

Output

Result Format

For each result, present:

  1. Source: File path or document name
  2. Score: BM25 relevance score (higher is better)
  3. Content: Relevant excerpt with matching terms highlighted

Read the full file on GitHub · 236 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. 4d ago First seen · 236 lines · 16 tokens per session scan A ef4d38f81b15

Subscribe to this mod's changes

agent-brain-bm25 is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 1,412 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.