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.
npx agentmods add commands/spillwavesolutions/agent-brain/agent-brain-keywordgit clone --depth 1 https://github.com/SpillwaveSolutions/agent-brainWrote 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.
[](https://agentmods.dev/commands/spillwavesolutions/agent-brain/agent-brain-keyword)<a href="https://agentmods.dev/commands/spillwavesolutions/agent-brain/agent-brain-keyword"><img src="https://agentmods.dev/badge/commands/spillwavesolutions/agent-brain/agent-brain-keyword.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00015 | $0.01156 |
| Opus 5 | $0.00008 | $0.00578 |
| Sonnet 5 | $0.00003 | $0.00231 |
| Haiku 4.5 | $0.00002 | $0.00116 |
Grade A, and why
agent-brain-keyword 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.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Brain Keyword Search
Purpose
Performs BM25 keyword search for fast, exact term matching. This mode is optimized for technical queries where you know the exact terms, function names, error codes, or identifiers.
Keyword search is ideal for:
- Error messages and codes
- Function and class names
- Configuration keys
- Technical identifiers
- When speed is critical (10-50ms response)
Usage
/agent-brain:agent-brain-keyword <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 Keyword Search
| Use Keyword/BM25 | Use Semantic 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 |
Execution
Pre-flight Check
Verify the server is running:
agent-brain status
Search Command
agent-brain query "<query>" --mode bm25 --top-k <top-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
# Search for multiple terms
agent-brain query "OAuth client_id redirect_uri" --mode bm25
Output
Format search results with source citations:
Result Format
For each result, present:
- Source: File path or document name
- Score: BM25 relevance score
- Content: Relevant excerpt with matching terms highlighted
Example Output
## Keyword Search Results for "AuthenticationError"
### 1. src/auth/exceptions.py (Score: 12.4)
class AuthenticationError(Exception):
"""Raised when authentication fails."""
def __init__(self, message: str, code: str = "AUTH_FAILED"):
self.code = code
super().__init__(message)
### 2. tests/test_auth.py (Score: 8.7)
def test_invalid_credentials_raises_authentication_error():
with pytest.raises(AuthenticationError) as exc:
auth_client.authenticate("invalid", "credentials")
assert exc.value.code == "AUTH_FAILED"
### 3. docs/errors/authentication.md (Score: 6.2)
## AuthenticationError
Raised when user credentials are invalid or expired.
**Common causes:**
- Invalid API key
- Expired token
- Missing credentials
---
Found 3 results
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.
- 4d ago First seen · 204 lines · 15 tokens per session scan A 0829bcb0932a
agent-brain-keyword is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 5d ago), licensed MIT. It adds 15 tokens to every session and 1,156 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.