brainstorm

brainstorm is a skill for Claude Code, Codex from nicknisi/ideation. It costs 165 tokens per session (961 once invoked), scanned A, original, MIT.

A conversation-based guide for deciding whether an idea is worth building. It examines assumptions, challenges the proposal, and helps clarify the desired outcome without writing files.

In plain words
What is it for?
Use it to pressure-test an idea, compare possible approaches, uncover missing considerations, and decide whether to proceed.
Why use it?
It helps separate a worthwhile problem from an unnecessary or over-engineered solution before planning implementation.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the ideation plugin — 7 skills, 3 agents 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/nicknisi/ideation/brainstorm
Any agent
npx skills add nicknisi/ideation --skill brainstorm
Clone the repo
git clone --depth 1 https://github.com/nicknisi/ideation

Made for: Claude Code, Codex.

Or install ideation, the plugin that ships this one along with the rest of its 7 skills, 3 agents.

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/nicknisi/ideation/brainstorm.svg)](https://agentmods.dev/skills/nicknisi/ideation/brainstorm)
Your own site
<a href="https://agentmods.dev/skills/nicknisi/ideation/brainstorm"><img src="https://agentmods.dev/badge/skills/nicknisi/ideation/brainstorm.svg" alt="Measured on agentmods" height="20"></a>
Per session 165 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 961 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 $0.00165 $0.00961
Opus 5 $0.00082 $0.00481
Sonnet 5 $0.00033 $0.00192
Haiku 4.5 $0.00016 $0.00096

Measured 5d ago against content hash 0669c539623c, 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.

skills/brainstorm/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brainstorm

A thinking partner for the stage before the interview: deciding whether to build, not planning how. It runs entirely in conversation and writes nothing.

Three moves, borrowed rather than restated. From ${CLAUDE_PLUGIN_ROOT}/references/interview-engine.md, read only these sections: Open by surfacing the silent assumptions, What to challenge during the interview, and Banned phrases — they apply verbatim. The over-engineering test is ${CLAUDE_PLUGIN_ROOT}/agents/plan-critic.md's over-engineering lens run in dialogue: argue for the minimum until the user names the goal that justifies more.

The rest of that engine is not yours. Its opening line says to execute every phase; that instruction is addressed to ideation, not to this skill. Skip Phase 1 Intake entirely — no parallel exploration sweep, no learnings read, no unmined-notes offer — and skip gate tracking, the scoreboard, the prototype and strawman escalations, and When to stop. You have no gates to track and nothing to hand back. To look something up, use Read/Glob/Grep, or an Agent with subagent_type: "Explore"; never a general-purpose subagent, which could write files this skill is built not to write. Agent names differ by harness — see ${CLAUDE_PLUGIN_ROOT}/references/harness-compat.md § 2: in pi, Explore becomes a read-only dispatch task (default tools — never edit/write/bash), never a writer task.

One fork at a time, in conversation. If you catch yourself wanting to capture the outcome as a file, that's the signal the stage is over — hand off.

Deliverable

A conclusion stated in chat — a few sentences, not a document — in four parts. This exact shape is what the ideation intake pre-seeds from, so land all four:

  1. The decision — build it, don't, or build the smaller thing instead — and the problem it solves, concretely enough to name who hits it, when, and what it costs them. That concreteness is the only part that can carry a gate on its own.
  2. The assumptions it rests on — what has to be true for the decision to hold.
  3. Alternatives rejected, and why — each becomes a contract decisions entry.
  4. Explicitly out — what we are not doing; becomes scope.outOfScope.

Read the full file on GitHub · 39 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 · 39 lines · 165 tokens per session scan A 0669c539623c

Subscribe to this mod's changes

brainstorm is a skill published in the GitHub repository nicknisi/ideation (13 stars, last pushed 2d ago), licensed MIT. It adds 165 tokens to every session and 961 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens