agent-brain-vector

A command that searches a code and document collection by meaning instead of requiring the exact words to match. It uses vector similarity, a method that compares the meaning of a query with indexed content.

In plain words
What is it for?
It is used to answer conceptual questions, find related documentation or code, and filter results by source type, language, path, or similarity score.
Why use it?
It helps find relevant material when you do not know the exact wording, file name, or terminology used in the source files.

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-vector
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,691 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 $0.00012 $0.01691
Opus 5 $0.00006 $0.00846
Sonnet 5 $0.00002 $0.00338
Haiku 4.5 $0.00001 $0.00169

Measured 2d ago against content hash 1bb8dd98f048, 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-vector 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-vector.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Performs semantic vector similarity search using embeddings. This mode understands meaning and concepts, finding relevant content even when exact terms don't match.

Vector search is ideal for:

  • Conceptual questions ("how does X work")
  • Natural language queries
  • Finding related content
  • Questions about purpose or design
  • When exact terms are unknown

Usage

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

Parameters

Parameter Required Default Description
query Yes - The conceptual search query
--top-k, -k No 5 Number of results (1-20)
--threshold, -t No 0.3 Minimum similarity (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)

When to Use Vector vs Other Modes

Use Vector Use BM25 Instead
"how does authentication work" "AuthenticationError"
"best practices for caching" "LRUCache"
"explain the deployment process" "deploy.yml"
"security considerations" "CVE-2024-1234"
"similar to user validation" "validate_user"

Execution

Pre-flight Check

# Verify server is running
agent-brain status

If not running:

agent-brain start

Search Command

agent-brain query "<query>" --mode vector --top-k <k> --threshold <t>

Examples

# Conceptual question
agent-brain query "how does the caching system work" --mode vector

# Natural language
agent-brain query "best practices for handling errors" --mode vector

# Find related content
agent-brain query "similar to user authentication flow" --mode vector

# Lower threshold for more results
agent-brain query "security considerations" --mode vector --threshold 0.2

# More results
agent-brain query "explain the API design" --mode vector --top-k 10

Read the full file on GitHub · 265 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 · 265 lines · 12 tokens per session scan A 1bb8dd98f048

Subscribe to this mod's changes

agent-brain-vector is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 1,691 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.