brainstorming

brainstorming is a skill for Claude Code, Codex from gerard-labs/superpowers-api-platform. It costs 0 tokens per session (552 once invoked), scanned A, original, MIT.

A planning aid for turning an unclear API feature idea into a clear development story. It explores requirements, fixed rules, possible approaches, unknowns, and the smallest useful first step before architecture work.

In plain words
What is it for?
Use it to clarify vague API stories, compare two or three approaches, identify risks, and prepare a description for architecture planning.
Why use it?
It prevents the team from committing to an implementation before agreeing on what the feature must do and which uncertainties matter.

Skill for Claude CodeCodex

Part of the gerard plugin — 53 skills, 25 commands, 7 agents, 1 hook 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/gerard-labs/superpowers-api-platform/brainstorming
Any agent
npx skills add gerard-labs/superpowers-api-platform --skill brainstorming
Clone the repo
git clone --depth 1 https://github.com/gerard-labs/superpowers-api-platform

Made for: Claude Code, Codex.

Or install gerard, the plugin that ships this one along with the rest of its 53 skills, 25 commands, 7 agents, 1 hook.

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 brainstorming

README.md
[![agentmods](https://agentmods.dev/badge/skills/gerard-labs/superpowers-api-platform/brainstorming.svg)](https://agentmods.dev/skills/gerard-labs/superpowers-api-platform/brainstorming)
Your own site
<a href="https://agentmods.dev/skills/gerard-labs/superpowers-api-platform/brainstorming"><img src="https://agentmods.dev/badge/skills/gerard-labs/superpowers-api-platform/brainstorming.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 552 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 $0.00552
Opus 5 $0.00000 $0.00276
Sonnet 5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured 4d ago against content hash 70467d2b3bd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brainstorming 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 4d 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/brainstorming/SKILL.md · 47 lines

What it actually says

Brainstorming (pre-architecture)

Use when

  • A story is too vague to feed /architect directly
  • You want to explore requirements + alternatives before committing to a plan
  • Multiple framings of the same feature exist; you want to pick one
  • The "smallest next step" is unclear

Position: this skill is upstream of the pipeline. Output = refined story description suitable for /architect <story> or /api-resource-pipeline <story>. Once the brainstorm converges, exit and feed the pipeline.

Default workflow

  1. Restate the story in your own words. Get explicit agreement on the goal.
  2. Surface invariants : what MUST be true at the end? (user-visible features + non-functional like perf, security, a11y).
  3. List alternatives : 2-3 ways to deliver the invariants. Compare on complexity / risk / time.
  4. Pick the smallest valuable slice : the smallest PR that surfaces the most risky hypothesis.
  5. Identify unknowns : what would falsify the design? Where are the spikes needed?
  6. Refine the story description — one paragraph, ready to feed /architect.

Guardrails

  • Stay upstream. Don't propose code, file paths, or skill dispatch — that's the architect's job.
  • Time-box the brainstorm. If you can't refine the story in 10 prompts, the story is too big — split it.
  • No premature pattern selection (CQRS vs simple service, DTO vs Object Mapper, etc.) — that's also the architect's decision.

Output contract

  • A refined story description (1 paragraph) usable as $ARGUMENTS of /architect.
  • A short list of explicit invariants + non-invariants ("nice to have" excluded).
  • A note on the smallest valuable slice.

Progressive disclosure

  • This file for the brainstorm flow
  • docs/complexity-tiers.md for sizing the brainstorm output

References

  • docs/complexity-tiers.md
  • docs/symfony/pipeline-overview.md — what happens after the brainstorm converges
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. 4d ago First seen · 47 lines · 0 tokens per session scan A 70467d2b3bd9

Subscribe to this mod's changes

brainstorming is a skill published in the GitHub repository gerard-labs/superpowers-api-platform (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 552 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.