brn

A short command for a focused brainstorming discussion about a software task, with a recommended way to carry the work forward.

In plain words
What is it for?
Use it to ask high-value questions, compare approaches, and choose an agent, worktree, and next development workflow.
Why use it?
It helps turn an unclear idea into an agreed design without creating a specification document.

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/artttj/rapid-stack/brn
Clone the repo
git clone --depth 1 https://github.com/artttj/rapid-stack
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 305 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 $0.00015 $0.00305
Opus 5 $0.00008 $0.00152
Sonnet 5 $0.00003 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured yesterday against content hash 37c419fe6b53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brn 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.

.opencode/commands/brn.md · 25 lines

What it actually says

Use the superpowers:brainstorming skill on the request below, but with these binding overrides (these are user instructions and take precedence over the skill's checklist):

  • Skip step 6 (do not write a spec doc)
  • Skip steps 7–8 (no spec self-review, no spec review gate)
  • Skip step 9 (do not invoke writing-plans)
  • Cap clarifying questions at 5 — pick the highest-signal ones
  • Present the design verbally only; do not propose creating any file

After the user approves the verbal design, add one final section: Recommended execution. In that section, propose the concrete next move:

  • Which agent to dispatch (e.g., code-reviewer, tdd-guide, feature-dev:code-architect, general-purpose for parallel exploration)
  • Whether the work fits a single agent, parallel subagents, or subagent-driven-development
  • Whether to open a git worktree first
  • Which skill to chain into next (tdd-workflow, executing-plans, etc.)

Pick one path and recommend it explicitly. Don't list every option neutrally.

If superpowers:brainstorming is not installed, run a 3-question Socratic dialogue, propose 2 approaches with the recommended one first, then add the Recommended execution section.

$ARGUMENTS

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. yesterday First seen · 25 lines · 15 tokens per session scan A 37c419fe6b53

Subscribe to this mod's changes

brn is a command published in the GitHub repository artttj/rapid-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 305 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 2026-08-31.