brainstorm

A guided conversation for deciding whether an idea is worth building before creating a product or code change.

In plain words
What is it for?
Use it to examine half-formed ideas, question proposed projects, and decide whether to proceed before writing a product requirements document or implementation plan.
Why use it?
It compares building nothing with building the proposal, including the ongoing cost and maintenance the new code would add. It can end with a clear decision not to build.

Skill for Claude CodeCodex

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/softspark/ai-toolkit/brainstorm
Any agent
npx skills add softspark/ai-toolkit --skill brainstorm
Clone the repo
git clone --depth 1 https://github.com/softspark/ai-toolkit

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,890 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 $0.00048 $0.01890
Opus 5 $0.00024 $0.00945
Sonnet 5 $0.00010 $0.00378
Haiku 4.5 $0.00005 $0.00189

Measured 2d ago against content hash bd5b52fbc9df, 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.

app/skills/brainstorm/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brainstorm

$ARGUMENTS

The conversation that happens before an artifact exists. Every other planning skill here produces something — a PRD, a plan, issues, a design. This one is allowed to produce nothing, and that is its point.

The zero option is a real candidate

Price "build nothing" against the proposal properly. Not as a strawman, not as a sentence acknowledged and moved past — as a genuine option with its own costs:

  • what breaks or stays broken if nobody does this
  • who currently absorbs that, and how much it costs them
  • how long the problem has existed without being fixed, and what that says about it
  • what the codebase carries forever once this exists: another surface, another migration path, another thing that has to keep working

If the zero option wins, say so and stop. Do not invent a deliverable to justify the conversation. A brainstorm that ends in "this is not worth building, and here is what it would have cost" has done its job.

Steps

Step 1: Understand before proposing

Explore the actual codebase before shaping anything. Read what exists, grep for prior attempts, check whether the problem is already solved somewhere.

Ask what the user is trying to achieve, not what they want built. The stated request is a proposed solution; the problem behind it is what matters. Keep asking until you can state the problem without naming the solution.

Step 2: Shape the options

Produce at least three genuinely different approaches, one of which is always "do nothing / do it manually / wait". Different means different in kind, not three variants of the same shape.

For each: what it costs, what it forecloses, what has to stay true for it to keep working.

Step 3: Resolve the unknowns

List what nobody in the conversation actually knows. For each, decide whether it can be resolved now (read the code, check the data, run something) or whether it stays open and becomes a risk the next stage inherits.

Resolve what is cheap to resolve. An unknown carried into a PRD becomes an Open Question; an unknown carried past a PRD becomes a bug.

Read the full file on GitHub · 175 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 · 175 lines · 48 tokens per session scan A bd5b52fbc9df

Subscribe to this mod's changes

brainstorm is a skill published in the GitHub repository softspark/ai-toolkit (167 stars, last pushed 4d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,890 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 2026-08-30.