brainstorm

A guided session for generating and recording ideas about a software feature. It can inspect the existing codebase first and saves the discussion in a Markdown file for later planning.

In plain words
What is it for?
Use it to explore feature ideas, gather relevant codebase context, and create notes before writing a formal specification or implementation plan.
Why use it?
It gives an open-ended idea session a clear structure and keeps the results in a place that specification and test-driven development planning can use.

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/pproenca/agent-tui/brainstorm
Clone the repo
git clone --depth 1 https://github.com/pproenca/agent-tui

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,065 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 $0.00009 $0.01065
Opus 5 $0.00005 $0.00532
Sonnet 5 $0.00002 $0.00213
Haiku 4.5 $0.00001 $0.00106

Measured 2d ago against content hash e846e7077153, 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 2d 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 · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brainstorm Command

Facilitate a structured brainstorming session and capture raw ideas into a discoverable artifact.

Artifact Location

All brainstorming artifacts are stored in: .claude/specs/<feature-name>/brainstorm.md

This location is used by downstream commands:

  • /spec <feature-name> reads from here to create formal specification
  • /plan-tdd <feature-name> can read the full chain

Execution Flow

Step 1: Setup

Extract feature name from argument: $ARGUMENTS

If no argument provided, use AskUserQuestion:

What feature or idea do you want to brainstorm?
- Short name (e.g., "plugin-system", "auth-flow", "real-time-sync")

Create directory: .claude/specs/<feature-name>/

Step 2: Context Gathering

Optionally explore the codebase to ground the brainstorm:

Use AskUserQuestion:

Should I explore the codebase first to understand relevant context?
○ Yes - explore architecture and patterns (Recommended)
○ No - start with blank slate

If yes, use Task tool with subagent_type=Explore to understand:

  • Current architecture relevant to the feature
  • Similar patterns already in codebase
  • Potential integration points

Step 3: Structured Brainstorming

Guide the user through these dimensions using AskUserQuestion and conversation:

3.1 Problem Space

Ask and capture:

  • What problem are we solving?
  • Who experiences this problem?
  • What's the impact of not solving it?
  • Are there workarounds today?
3.2 Solution Space

Ask and capture:

  • What's the ideal end state?
  • What are possible approaches?
  • What similar solutions exist (in this codebase or elsewhere)?
  • What are the trade-offs between approaches?
3.3 Constraints

Ask and capture:

  • Technical constraints (performance, compatibility, dependencies)
  • Business constraints (timeline, resources, scope)
  • User constraints (learning curve, migration path)
3.4 Risks & Unknowns

Ask and capture:

  • What could go wrong?
  • What don't we know yet?
  • What needs prototyping or research?

Read the full file on GitHub · 221 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. 2d ago First seen · 221 lines · 9 tokens per session scan A e846e7077153

Subscribe to this mod's changes

brainstorm is a command published in the GitHub repository pproenca/agent-tui (113 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 1,065 once invoked, about $0.0000 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.