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-helpgit clone --depth 1 https://github.com/SpillwaveSolutions/agent-brainWhat 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 | $0.00012 | $0.01523 |
| Opus 5 | $0.00006 | $0.00762 |
| Sonnet 5 | $0.00002 | $0.00305 |
| Haiku 4.5 | $0.00001 | $0.00152 |
Grade A, and why
agent-brain-help 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Brain Help
Purpose
Displays available Agent Brain commands and usage information. Without parameters, shows a summary of all commands. With a specific command name, shows detailed help for that command.
Usage
/agent-brain:agent-brain-help [--command <name>]
Parameters
| Parameter | Required | Default | Description |
|---|---|---|---|
| --command | No | - | Specific command to get detailed help for |
Examples
/agent-brain:agent-brain-help # Show all commands
/agent-brain:agent-brain-help --command search # Detailed help for search
/agent-brain:agent-brain-help --command index # Detailed help for index
Execution
Without Parameters: Show All Commands
Display the complete command reference:
Agent Brain Commands
====================
SEARCH COMMANDS
agent-brain-search Hybrid BM25+semantic search (recommended default)
agent-brain-bm25 Pure BM25 keyword search for exact terms
agent-brain-keyword Alias for BM25 keyword search
agent-brain-hybrid Hybrid BM25+semantic with alpha tuning
agent-brain-graph GraphRAG relationship search (requires ENABLE_GRAPH_INDEX=true)
SETUP COMMANDS
agent-brain-install Install Agent Brain packages from PyPI
agent-brain-config View and manage provider configuration
agent-brain-init Initialize Agent Brain for current project
SERVER COMMANDS
agent-brain-start Start the Agent Brain server for this project
agent-brain-stop Stop the running server
agent-brain-status Show server status, port, and document count
agent-brain-list List all running Agent Brain instances
INDEXING COMMANDS
agent-brain-index Index documents for search
agent-brain-inject Index documents with content injection (scripts/metadata)
agent-brain-folders Manage indexed folders (list, add, remove)
agent-brain-types List available file type presets
agent-brain-jobs Monitor and manage async indexing jobs
agent-brain-reset Clear the document index (requires confirmation)
CACHE COMMANDS
agent-brain-cache View cache metrics or clear embedding cache
RUNTIME COMMANDS
agent-brain-install-agent Install plugin for a runtime (Claude, OpenCode, Gemini, Codex, skill-runtime)
agent-brain-uninstall Uninstall Agent Brain plugin files
HELP
agent-brain-help Show this help message
Use '/agent-brain:agent-brain-help --command <name>' for detailed help on any command.
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.
- 2d ago First seen · 187 lines · 12 tokens per session scan A 1d3c382a495b
agent-brain-help is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 3d ago), licensed MIT. It adds 12 tokens to every session and 1,523 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
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.