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

.agents/skills/brainstorming/SKILL.md

brainstorming is a skill for Claude Code, Codex from systemowiec/ai-agents-workspace-starter. It costs 29 tokens per session (565 once invoked), scanned A, original, MIT.

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.

In plain words
What is it for?
Use it when planning features, refactors, API changes, new modules, services, or infrastructure changes.
Why use it?
It exposes missing assumptions and design decisions early, reducing the risk of quick fixes that cause regressions or need to be rewritten.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is systemowiec/ai-agents-workspace-starter's own configuration. It tells Claude Code and Codex how to work on ai-agents-workspace-starter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-agents-workspace-starter configures →

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.

agentmods badge for brainstorming

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.

agentmods 80×15 button for brainstorming

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00565
Opus 5 $0.00015 $0.00282
Sonnet 5 $0.00006 $0.00113
Haiku 4.5 $0.00003 $0.00056

Measured 10d ago against content hash b035baf23924, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

  1. 10d 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 5mo ago), licensed MIT. It adds 29 tokens to every session and 565 once invoked, about $0.0001 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.

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens