brainstorm

brainstorm is a command for coding agents from mrvladd-d/memobank. It costs 17 tokens per session (757 once invoked), scanned A, original, MIT.

A guided thinking session for turning a rough product idea into a structured brainstorming report. The AI facilitates the discussion, while you provide the product intent and make the decisions.

In plain words
What is it for?
Use it to explore a raw idea, clarify the problem, compare directions, and record open questions or risks before creating a product brief.
Why use it?
It helps when the problem is unclear or there are too many possible directions, without turning untested ideas into requirements too early.

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/mrvladd-d/memobank/brainstorm
Clone the repo
git clone --depth 1 https://github.com/mrvladd-d/memobank

Wrote 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.

agentmods badge for brainstorm

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrvladd-d/memobank/brainstorm.svg)](https://agentmods.dev/commands/mrvladd-d/memobank/brainstorm)
Your own site
<a href="https://agentmods.dev/commands/mrvladd-d/memobank/brainstorm"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/brainstorm.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 757 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 $0.00017 $0.00757
Opus 5 $0.00009 $0.00378
Sonnet 5 $0.00003 $0.00151
Haiku 4.5 $0.00002 $0.00076

Measured 4d ago against content hash 172eeeecc623, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

skills/_shared/references/commands/brainstorm.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/brainstorm - Facilitated ideation

The AI is a facilitator and coach. The user is the source of product intent, priorities, and decisions. Raw ideas do not become requirements directly.

0) Scope

Use /brainstorm when the idea is raw, the problem space is unclear, or there are too many possible directions.

Do not create:

  • PRD
  • Product Brief, unless the user separately invokes /brief
  • task records
  • implementation plans
  • research reports
  • PRFAQ
  • .memory-bank/analysis/assumptions.md
  • command aliases

No research mode. If research is needed, record it as an open question or risk.

1) Prepare artifacts

Create if missing:

  • .memory-bank/analysis/index.md
  • .memory-bank/analysis/brainstorming/

When creating .memory-bank/analysis/index.md, include:

---
description: Analysis artifact index.
status: active
---

Create a new report:

.memory-bank/analysis/brainstorming/BR-001.md

If BR-001.md exists, use the next available ID: BR-002.md, BR-003.md, and so on.

Update .memory-bank/analysis/index.md with the latest report link and:

Recommended next step: /brief

2) Facilitate, do not invent

Start by asking for or confirming:

  • problem space
  • target users
  • user goals
  • constraints
  • what the user already believes or wants to avoid

Use lightweight ideation only as needed:

  • alternative user journeys
  • pain points
  • solution directions
  • constraints-first thinking
  • risk-first thinking
  • MVP slicing

Default target is 20-40 useful ideas or directions only when expansion is useful. If the user already has a clear direction, keep the session short.

3) Report structure

Write the report with these sections:

---
description: Brainstorming report BR-<NNN>.
status: active
type: brainstorming-report
id: BR-<NNN>
---
# Brainstorming Report - BR-<NNN>

## Status
- Date: YYYY-MM-DD
- Facilitator: AI
- Source of product intent: user
- Recommended next step: /brief

## Problem Space

## Goals

## Constraints

## Techniques Used

## Raw Ideas

## Clusters / Themes

## Selected Directions

## Rejected Directions

## Assumptions

## Open Questions

## Recommended Next Step
/brief

Read the full file on GitHub · 131 lines

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. 4d ago First seen · 131 lines · 17 tokens per session scan A 172eeeecc623

Subscribe to this mod's changes

brainstorm is a command published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 757 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.