brainstorm

brainstorm is a command for coding agents from rafaelkamimura/claude-tools. It costs 0 tokens per session (2,767 once invoked), scanned A, original, MIT.

A command for exploring an implementation idea through an interactive brainstorming session, with notes saved for later reference.

In plain words
What is it for?
Use it to gather requirements, compare possible solutions, examine feasibility, and preserve the discussion before implementation.
Why use it?
It gives unclear ideas a structured place to develop before you commit to a design or start coding.

Command

Part of the claude-tools plugin — 12 commands, 46 agents shipped together

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/rafaelkamimura/claude-tools/brainstorm
Clone the repo
git clone --depth 1 https://github.com/rafaelkamimura/claude-tools

Or install claude-tools, the plugin that ships this one along with the rest of its 12 commands, 46 agents.

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/rafaelkamimura/claude-tools/brainstorm.svg)](https://agentmods.dev/commands/rafaelkamimura/claude-tools/brainstorm)
Your own site
<a href="https://agentmods.dev/commands/rafaelkamimura/claude-tools/brainstorm"><img src="https://agentmods.dev/badge/commands/rafaelkamimura/claude-tools/brainstorm.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,767 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 $0.00000 $0.02767
Opus 5 $0.00000 $0.01384
Sonnet 5 $0.00000 $0.00553
Haiku 4.5 $0.00000 $0.00277

Measured 3d ago against content hash 1085a6d6a819, 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 3d 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.

commands/brainstorm.md · 514 lines

How it starts

The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brainstorm Session

Deep thinking command for exploring implementation ideas, analyzing possibilities, and capturing creative solutions with context preservation.

Purpose

  • Ultra-deep analysis of implementation ideas
  • Interactive requirement gathering
  • Possibility and feasibility exploration
  • Context preservation for future reference
  • Transition to implementation when ready

Workflow

Phase 1: Session Initialization

  1. STOP → "What would you like to brainstorm about?"

    • Wait for user to provide initial concept/idea
  2. Generate Session ID

    # Create unique session identifier
    timestamp=$(date +%Y%m%d_%H%M%S)
    session_id="bs_${timestamp}"
    
    # Extract short description from prompt
    description=$(echo "$prompt" | head -c 30 | tr ' ' '-' | tr -cd '[:alnum:]-')
    filename="brainstorm-${description}"
    
  3. Save Initial Prompt

    mkdir -p .claude/brainstorms
    echo "# Brainstorm: $prompt" > .claude/brainstorms/${filename}.md
    echo "**Session ID**: $session_id" >> .claude/brainstorms/${filename}.md
    echo "**Date**: $(date)" >> .claude/brainstorms/${filename}.md
    echo "**Status**: Active" >> .claude/brainstorms/${filename}.md
    

Phase 2: Ultra-Deep Thinking Mode

  1. Activate Deep Analysis Deploy specialized agents for comprehensive analysis:

    • backend-architect: System design implications
    • frontend-developer: UI/UX considerations
    • database-optimizer: Data structure needs
    • security-auditor: Security implications
    • performance-engineer: Performance considerations
    • test-automator: Testing strategies
  2. Multi-Dimensional Analysis

    ULTRA-THINK DIMENSIONS:
    
    1. Technical Feasibility
       - Architecture patterns
       - Technology stack options
       - Integration points
       - Scalability considerations
    
    2. Implementation Complexity
       - Time estimates
       - Resource requirements
       - Skill dependencies
       - Risk factors
    
    3. Business Impact
       - User value
       - Performance implications
       - Maintenance burden
       - Cost-benefit analysis
    
    4. Alternative Approaches
       - Different solutions
       - Trade-offs
       - Hybrid approaches
       - Incremental paths
    

Read the full file on GitHub · 514 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. 3d ago First seen · 514 lines · 0 tokens per session scan A 1085a6d6a819

Subscribe to this mod's changes

brainstorm is a command published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,767 tokens. 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.