agent-brain-semantic

A command for meaning-based search in Agent Brain using vector representations, which compare the concepts in a query with the concepts in documents. It can find related text even when the exact words differ.

In plain words
What is it for?
Use it to search conceptual questions, find related documents, filter by source type, language, or file path, and inspect similarity scores or full text.
Why use it?
It helps answer natural-language questions and discover related documentation when keyword matching misses relevant wording. Results can be filtered and scored.

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-semantic
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,297 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 $0.00014 $0.01297
Opus 5 $0.00007 $0.00648
Sonnet 5 $0.00003 $0.00259
Haiku 4.5 $0.00001 $0.00130

Measured 2d ago against content hash e145fe828191, 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-semantic 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-semantic.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Performs pure semantic vector search using OpenAI embeddings. This mode finds documents based on meaning and conceptual similarity rather than exact keyword matching.

Semantic search is ideal for:

  • Conceptual questions ("how does X work?")
  • Finding related documentation even without exact term matches
  • Natural language queries
  • Discovering documents about similar concepts

Usage

/agent-brain:agent-brain-semantic <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 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)

When to Use Semantic Search

Use Semantic Search Use BM25/Keyword Instead
"how does authentication work" "AuthenticationError"
"best practices for caching" "cache_ttl_seconds"
"explain the data model" "UserSchema"
"what is the purpose of..." exact function names

Execution

Pre-flight Check

Verify the server is running and has indexed documents:

agent-brain status

Expected output shows:

  • Server status: healthy
  • Document count: > 0
  • Mode: project or shared

Search Command

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

Examples

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

# More results for broader exploration
agent-brain query "best practices for error handling" --mode vector --top-k 10

# Higher threshold for more precise matches
agent-brain query "explain caching strategy" --mode vector --threshold 0.5

# Lower threshold to find tangentially related docs
agent-brain query "security considerations" --mode vector --threshold 0.2

Read the full file on GitHub · 207 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 · 207 lines · 14 tokens per session scan A e145fe828191

Subscribe to this mod's changes

agent-brain-semantic is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 1,297 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.