brainstorm

brainstorm is a command for Claude Code from nimble-giant/ailloy. It costs 0 tokens per session (2,462 once invoked), scanned A, original, Apache-2.0.

A structured analysis of a raw software idea before implementation.

In plain words
What is it for?
It is for turning a prompt into a hypothesis, high-level solution options, diagrams, reports, and other decision-support notes.
Why use it?
It exposes feasibility, scope, expected value, and possible problems before development work begins.

Command for Claude Code

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/nimble-giant/ailloy/brainstorm
Clone the repo
git clone --depth 1 https://github.com/nimble-giant/ailloy

Made for: Claude Code.

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/nimble-giant/ailloy/brainstorm.svg)](https://agentmods.dev/commands/nimble-giant/ailloy/brainstorm)
Your own site
<a href="https://agentmods.dev/commands/nimble-giant/ailloy/brainstorm"><img src="https://agentmods.dev/badge/commands/nimble-giant/ailloy/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 2,462 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 $0.02462
Opus 5 $0.00000 $0.01231
Sonnet 5 $0.00000 $0.00492
Haiku 4.5 $0.00000 $0.00246

Measured 5d ago against content hash a6fd474f81fe, 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 5d 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.

.claude/commands/brainstorm.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brainstorm

Purpose

This command takes a raw idea or prompt and systematically dissects it using structured brainstorming techniques inspired by the UNC Writing Center's brainstorming methodology. It analyzes the idea for feasibility, scope, and predicted value, extracts a hypothesis, and proposes high-level solutions. If the idea is not viable, it says so directly.

This command produces supporting artifacts only — not implementation. The output is documentation, analysis reports, diagrams, and structured findings that help the user decide whether and how to proceed. The user takes implementation as a separate, deliberate act.

Command Name

brainstorm

Invocation Syntax

/brainstorm <idea or prompt>

Examples

/brainstorm a CLI tool that auto-generates changelogs from conventional commits
/brainstorm adding real-time collaboration to our document editor
/brainstorm replacing our REST API with GraphQL
/brainstorm a service that monitors GitHub Actions costs and suggests optimizations

Workflow

When this command is invoked, Claude must:

  1. Enter Plan Mode immediately
  2. Execute all brainstorming phases below against the user's idea
  3. Present the complete brainstorm analysis as the plan using ExitPlanMode
  4. Wait for user approval
  5. After approval, save the brainstorm report and stop. Do not begin implementation. The user decides if and when to act on the findings separately

Report Save Location

Save the final report to:

  • .claude/plans/ if a .claude/ directory exists in the project root
  • ~/.claude/plans/ otherwise

Create the plans/ subdirectory if it does not exist.

Report File Naming

Name the file brainstorm-{slug}.md where {slug} is a kebab-case summary of the idea (3-5 words max), derived from the core idea — not randomly generated.

Examples:

  • "a CLI tool that auto-generates changelogs from conventional commits" → brainstorm-cli-changelog-generator.md
  • "adding real-time collaboration to our document editor" → brainstorm-realtime-doc-collaboration.md
  • "personal AI assistant" → brainstorm-personal-ai-assistant.md

Read the full file on GitHub · 271 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. 5d ago First seen · 271 lines · 0 tokens per session scan A a6fd474f81fe

Subscribe to this mod's changes

brainstorm is a command published in the GitHub repository nimble-giant/ailloy (10 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,462 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.