What is brainstorming?

A conversation-led process for turning an idea into an agreed design before coding begins. It examines the project, clarifies requirements, and proposes how the change should work.

Use it when planning features, refactors, API changes, new modules, services, or infrastructure changes.

It exposes missing assumptions and design decisions early, reducing the risk of quick fixes that cause regressions or need to be rewritten.

How systemowiec/ai-agents-workspace-starter configures Claude Code and

Reuse

Borrowing it

Nothing to install: this file belongs to systemowiec/ai-agents-workspace-starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/systemowiec/ai-agents-workspace-starter/main/.agents/skills/brainstorming/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/systemowiec/ai-agents-workspace-starter

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/systemowiec/ai-agents-workspace-starter/brainstorming/github.svg)](https://agentmods.dev/skills/systemowiec/ai-agents-workspace-starter/brainstorming)

Your own site

<a href="https://agentmods.dev/skills/systemowiec/ai-agents-workspace-starter/brainstorming"><img src="https://agentmods.dev/badge/skills/systemowiec/ai-agents-workspace-starter/brainstorming/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/systemowiec/ai-agents-workspace-starter/brainstorming"><img src="https://agentmods.dev/badge/skills/systemowiec/ai-agents-workspace-starter/brainstorming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 565 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.00565
Opus 5.5	$0.00012	$0.00226
Sonnet 5.5	$0.00006	$0.00113
Haiku 4.5	$0.00003	$0.00056

Measured 2mo ago against content hash b035baf23924, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

.agents/skills/brainstorming/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brainstorming - Design Before Code

Overview

Help transform ideas into fully refined concepts through natural dialogue. Understand the project context, ask questions, propose solutions, get approval BEFORE coding.

HARD GATE: DO NOT CODE before the design is approved. Applies to EVERY project regardless of perceived simplicity.

When to Use

New feature to implement
Refactor requiring architectural decisions
API contract change
New module or service
Infrastructure change

When NOT to use:

Bugfix with a clear cause
Configuration change
Documentation update

Red Flags - if you're thinking this, STOP

Thought	Reality
"This is too simple for a design"	Simple things = unexplored assumptions. The design can be short.
"I already know what to do"	Knowledge != plan. Write the design.
"I'll quickly fix this"	Quick fixes without design = regression
"User wants it done, not planned"	The instruction says WHAT, not HOW. The design says HOW.

Process

1. Explore the project context

Check files, docs, recent commits
Read .agents/context/project-overview.md
Identify related modules

2. Ask questions - ONE at a time

Don't overwhelm with multiple questions
Prefer multiple-choice questions
Focus on: goal, constraints, success criteria

3. Propose 2-3 approaches

Present options with trade-offs
Lead with the recommended option and justification
Consider YAGNI - remove unnecessary features

4. Present the design

Scale each section to complexity
After each section ask if it looks good
Cover: architecture, components, data flow, error handling, tests

5. Save the design

Save to docs/specs/{layer}/{PREFIX}-NNN/ (create via workflow create-spec.md if needed)
Commit the design document

6. Proceed to implementation

Create an implementation plan (workflow spec-development.md)
DO NOT code without a plan

Key Principles

One question at a time - don't overwhelm
YAGNI ruthlessly - remove unnecessary features from every design
Explore alternatives - always 2-3 approaches
Incremental validation - present, get approval, move on

Read the full file on GitHub · 78 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.

2mo ago First seen · 78 lines · 29 tokens per session scan A b035baf23924

Subscribe to this mod's changes

brainstorming is a skill published in the GitHub repository systemowiec/ai-agents-workspace-starter (2 stars, last pushed 7mo ago), licensed MIT. It adds 29 tokens to every session and 565 once invoked, about $0.0001 per session on Opus 5.5. 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.

Planning

brainstorming next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
brainstormingsystemowiec/ai-agents-workspace-starter	Skill	2	7mo ago	MIT	A	29	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex

ai-agents-workspace-starter: Skill for Claude Code