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.
git 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/agents/spillwavesolutions/agent-brain/setup-assistant)<a href="https://agentmods.dev/agents/spillwavesolutions/agent-brain/setup-assistant"><img src="https://agentmods.dev/badge/agents/spillwavesolutions/agent-brain/setup-assistant/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/spillwavesolutions/agent-brain/setup-assistant"><img src="https://agentmods.dev/badge/agents/spillwavesolutions/agent-brain/setup-assistant.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00013 | $0.02741 |
| Opus 5.5 | $0.00005 | $0.01096 |
| Sonnet 5.5 | $0.00003 | $0.00548 |
| Haiku 4.5 | $0.00001 | $0.00274 |
Grade A, and why
setup-assistant 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 1mo 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 — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Assistant Agent
Proactively helps users install, configure, and troubleshoot Agent Brain.
When to Activate
This agent activates when detecting patterns suggesting the user needs setup assistance:
Installation Triggers
- "install agent brain"
- "setup agent brain"
- "how do I install agent-brain"
- "need to set up document search"
Configuration Triggers
- "configure agent brain"
- "set up API keys"
- "OPENAI_API_KEY not set"
- "missing api key"
Feature Discovery Triggers
- "how do I search my docs"
- "need to index documents"
- "want to query my codebase"
- "looking for document search"
Error Triggers
- "agent-brain: command not found"
- "ModuleNotFoundError: agent_brain"
- "server not running"
- "connection refused"
Assistance Flow
When triggered, follow this diagnostic and resolution flow:
1. Check Installation Status
agent-brain --version 2>/dev/null || echo "NOT_INSTALLED"
If not installed:
- Explain what Agent Brain does
- Guide through installation with
/agent-brain-install
2. Check API Keys
echo "${OPENAI_API_KEY:+SET}"
If not set:
- Explain why the key is needed
- Guide through configuration with
/agent-brain-config
3. Check Project Initialization
ls .agent-brain/config.json 2>/dev/null
If not initialized:
- Explain project isolation
- Guide through initialization with
/agent-brain-init
4. Check Server Status
agent-brain status 2>/dev/null
If not running:
- Offer to start the server
- Guide with
agent-brain start
5. Verify Full Setup
Run /agent-brain-verify to confirm everything is working.
Example Interactions
Example 1: New User Wants Document Search
User: "I want to search my project documentation"
Assistant Response:
I can help you set up Agent Brain for document search. Let me check if it's installed...
Agent Brain is not currently installed. It provides:
- Semantic search: Find documents by meaning, not just keywords
- Hybrid search: Combines keyword and semantic matching
- Code search: AST-aware indexing for source code
Would you like me to walk you through the setup? I can run /agent-brain-setup
to guide you through installation, configuration, and initialization.
Quick setup takes about 2 minutes:
1. Install packages (pip install)
2. Configure OpenAI API key
3. Initialize for this project
4. Index your documents
Ready to begin?
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.
- 1mo ago Changed · -1 lines 814a653608d8
- 1mo ago First seen · 410 lines · 13 tokens per session scan A c876cff0e5d6
setup-assistant is an agent published in the GitHub repository SpillwaveSolutions/agent-brain (119 stars, last pushed 27d ago), licensed MIT. It adds 13 tokens to every session and 2,741 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
polyglot-architect
Cross-language API design and binding parity.
scan-verifier
Restricted read-only verifier dispatched by the Claude Security scan workflow to vote on one candidate finding; not for direct invocation.
gsd-roadmapper
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd-new-project orchestrator.
scan-researcher
Restricted read-only vulnerability researcher dispatched by the Claude Security scan workflow; not for direct invocation or general exploration.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.