brainstorm

brainstorm is a skill for Claude Code, Codex from chipweaver/veripower. It costs 39 tokens per session (1,248 once invoked), scanned A, original, MIT.

A guided conversation for deciding the requirements and technical structure of a new software module before development begins. It saves the agreed decisions in a brainstorm.md file.

In plain words
What is it for?
Use it to discuss a module's goals, requirements, and architecture, or to revise those decisions when a later part of the development process finds a contradiction.
Why use it?
It helps resolve unclear or conflicting requirements before they spread into design and code.

Skill for Claude CodeCodex

Part of the veripower plugin — 12 skills, 3 hooks 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 skills/chipweaver/veripower/brainstorm
Any agent
npx skills add chipweaver/veripower --skill brainstorm
Clone the repo
git clone --depth 1 https://github.com/chipweaver/veripower

Made for: Claude Code, Codex.

Or install veripower, the plugin that ships this one along with the rest of its 12 skills, 3 hooks.

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/skills/chipweaver/veripower/brainstorm.svg)](https://agentmods.dev/skills/chipweaver/veripower/brainstorm)
Your own site
<a href="https://agentmods.dev/skills/chipweaver/veripower/brainstorm"><img src="https://agentmods.dev/badge/skills/chipweaver/veripower/brainstorm.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,248 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 $0.00039 $0.01248
Opus 5 $0.00019 $0.00624
Sonnet 5 $0.00008 $0.00250
Haiku 4.5 $0.00004 $0.00125

Measured 3d ago against content hash e495c8638c42, 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.

skills/brainstorm/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-Pipeline Requirements Brainstorm

Own the interactive D0–D7 brainstorm dialogue and produce a frozen {module}/brainstorm.md. Run in your own session, before the design pipeline: the brainstorm conversation never enters the pipeline's context. The pipeline starts when the user starts it and reads that file solely inside its sub-agent contexts (it is the pipeline's input, not a pipeline stage).

When to Use

  • A new module needs its requirements + architecture settled before the pipeline.
  • A requirements contradiction surfaced downstream and was escalated for revision: the user aborts, re-invokes this skill in revision mode, re-approves.

Iron Rule

  • You are pre-pipeline: write exactly one artifact, {module}/brainstorm.md (creating {module} if absent, before the module enters the pipeline). Write no result.json, and you are not a pipeline stage — you run before any pipeline state exists.
  • Do not author design.md / RTL / constraints / any downstream artifact. Your output is the brainstorm only; design.md is derived from it downstream.
  • brainstorm.md is frozen for the duration of a run. A requirements change is handled by re-invoking this skill in revision mode, never by editing an in-flight artifact to absorb the change: every proof downstream records the fingerprint it read.

Input Artifacts

Variable / input Purpose
{module} The module's directory — the same path the pipeline is later given as --module, and where its whole work tree goes. Anywhere the user wants: ~/chips/mydesign, ./mychip, asic/mychip. Its last component is the module name, which titles the brainstorm.
User-provided material (optional) Public spec / reference docs the user pastes or points to.

No fixed external inputs. Revision mode additionally reads the existing {module}/brainstorm.md.

Ask for the directory if the user named only a module. Do not invent a parent for them: nothing downstream imposes one, and a guess sends them looking for a tree they did not ask for.

Read the full file on GitHub · 115 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 115 lines · 39 tokens per session scan A e495c8638c42

Subscribe to this mod's changes

brainstorm is a skill published in the GitHub repository chipweaver/veripower (4 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 1,248 once invoked, about $0.0002 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.