brainstorm

A guided brainstorming command for exploring a topic with selectable depth and focus. It can cover features, architecture, user experience, APIs, interfaces, or operations, and can capture the result as an implementation specification.

In plain words
What is it for?
Use it to develop feature ideas, define MVP scope and acceptance criteria, sketch system designs, explore user interfaces, plan APIs, or save a discussion as a specification.
Why use it?
It gives an open-ended idea session a time limit, a chosen area, and a clear level of detail, helping turn vague thoughts into questions and an actionable plan.

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/data-wise/claude-plugins/brainstorm
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/claude-plugins
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,563 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 $0.00023 $0.08563
Opus 5 $0.00012 $0.04281
Sonnet 5 $0.00005 $0.01713
Haiku 4.5 $0.00002 $0.00856

Measured yesterday against content hash e3e5e584c579, 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 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.

workflow/commands/brainstorm.md · 1,132 lines

How it starts

The opening of the file, as written. The whole thing — 1,132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/workflow:brainstorm - Enhanced Brainstorm

ADHD-friendly brainstorming with smart mode detection, time budgets, agent delegation, and spec capture for implementation.

Arguments (v2.3.0 - Three-Layer System)

/brainstorm [depth] [focus] [action] "topic"
            ↑       ↑       ↑
            │       │       └── s|save (capture as spec)
            │       └────────── f|feat|a|arch|x|ux|b|api|u|ui|o|ops
            └────────────────── q|quick|d|deep|m|max

Depth Layer

Full Short Single Time Description
(default) - - < 5 min Balanced, 2 questions + "ask more?"
quick quick q < 1 min Fast, 0 questions + "ask more?"
deep deep d < 10 min Expert questions (8), no agents
max max m < 30 min Expert questions + 2 agents

Note: thorough is deprecated alias for max

Focus Layer

Full Short Single What it brainstorms
(auto) - - Auto-detect from context
feature feat f User stories, MVP scope, acceptance criteria
architecture arch a System design, scalability, component diagrams
ux ux x UI/UX wireframes, accessibility, user flows
api api b API endpoints, database schema, auth patterns
ui ui u Component tree, state management, performance
ops ops o CI/CD pipelines, deployment, infrastructure

Synonyms: designux, backendapi, frontendui, devopsops

Action Layer

Full Short Single What it does
(none) - - Output BRAINSTORM.md only
save save s Output SPEC.md (replaces --save-spec)

Synonym: specsave

Quick Examples

# Minimal
/brainstorm "auth"              # Default everything

# With focus
/brainstorm feat "auth"         # Feature focus
/brainstorm f "auth"            # Same (single letter)

# With action
/brainstorm save "auth"         # Save as spec
/brainstorm s "auth"            # Same (single letter)

# Combined
/brainstorm feat save "auth"    # Feature + spec
/brainstorm f s "auth"          # Same (ultra-short)

# Full control
/brainstorm deep feat save "auth"   # Deep + feature + spec
/brainstorm d f s "auth"            # Power user mode

# Maximum depth
/brainstorm max arch save "auth"    # Max + architecture + spec
/brainstorm m a s "auth"            # Same (ultra-short)

Read the full file on GitHub · 1,132 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. yesterday First seen · 1,132 lines · 23 tokens per session scan A e3e5e584c579

Subscribe to this mod's changes

brainstorm is a command published in the GitHub repository Data-Wise/claude-plugins (7 stars, last pushed 5d ago), licensed MIT. It adds 23 tokens to every session and 8,563 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.