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/smart-ai-memory/attune-ai/brainstormgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/smart-ai-memory/attune-ai/brainstorm)<a href="https://agentmods.dev/commands/smart-ai-memory/attune-ai/brainstorm"><img src="https://agentmods.dev/badge/commands/smart-ai-memory/attune-ai/brainstorm.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 | $0.00012 | $0.01415 |
| Opus 5 | $0.00006 | $0.00707 |
| Sonnet 5 | $0.00002 | $0.00283 |
| Haiku 4.5 | $0.00001 | $0.00142 |
Grade A, and why
brainstorm 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 yesterday.
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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brainstorm
Guided brainstorming that turns fuzzy thinking into concrete plans.
One conversation. Clear outcome.
How It Works
Type /brainstorm and I'll think through the problem with
you. We'll move through four natural phases and end with
an artifact you can act on.
/brainstorm # Start open discovery
/brainstorm "flaky CI tests" # Start with context
/brainstorm plan # Jump closer to planning
Conversation Flow
Opening
I'll help you think this through. We'll explore the problem, clarify goals, and end with a concrete plan you can act on.
What are you working on?
Phases
The conversation moves through four phases. Show a breadcrumb for orientation. Use soft checkpoints when alignment is uncertain.
Breadcrumb format:
Context > Problem > Goals > End State > Plan
done here
| Phase | AI's Job | Advance when... |
|---|---|---|
| Context | Listen, ask follow-ups, understand the situation | Situation is clear |
| Problem | Mirror back understanding, challenge assumptions | Core issue is agreed on |
| Goals | Distinguish must-haves from nice-to-haves | Success criteria defined |
| End State | Make it concrete and testable | "Done" is unambiguous |
AI Behavior Rules
Three moves per turn — pick one:
- Mirror — "So the core issue is X" (confirm understanding)
- Challenge — "But is it actually Y?" (push deeper, question assumptions)
- Advance — "OK, what does done look like?" (move to next phase)
Transition rules:
- Default: Show breadcrumb, advance naturally
- When uncertain: Soft checkpoint — "Here's what I'm
hearing... does that sound right?" Use this when:
- Answers are vague or contradictory
- Scope keeps shifting
- High-stakes decisions are involved
- Never announce phase names or say "entering phase 3"
- Never rush — stay in a phase until it has genuine clarity
Conversation principles:
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.
- yesterday First seen · 215 lines · 12 tokens per session scan A 5acfd0a881c8
brainstorm is a command published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 12 tokens to every session and 1,415 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 2026-09-03.
Other commands, from other repositories
ship-and-babysit
Commit, push to origin (fork), open PR to tinyhumansai/openhuman:main, then poll every 5min for CodeRabbit comments and CI failures, resolve them, and exit when clean.
agentos-status
Show AgentOS system status — agents, workers, health.
council-sweep
Walk the configured watch paths and run Council on every artifact modified in the last N hours (default 24h).
orchestrate
Orchestrate a complex multi-step task using the multi-agent system.
pm-agent-retire
Mark a great-pm agent as deprecated. Adds a deprecation banner to the agent file, files a Beads issue to remove dependent commands/workflows, and logs the rationale. NEVER deletes the file (history preserved).
explain
Generate an interactive one-module explainer for a topic — Riko gathers code scope, Senku plans a 3-5 screen teaching arc, Speedwagon authors the HTML, assembler produces explain-out/index.html.