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.
npx skills add yuchenbigpen1/normies --skill brainstorminggit clone --depth 1 https://github.com/yuchenbigpen1/normiesWrote 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.
[](https://agentmods.dev/skills/yuchenbigpen1/normies/brainstorming)<a href="https://agentmods.dev/skills/yuchenbigpen1/normies/brainstorming"><img src="https://agentmods.dev/badge/skills/yuchenbigpen1/normies/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.
<a href="https://agentmods.dev/skills/yuchenbigpen1/normies/brainstorming"><img src="https://agentmods.dev/badge/skills/yuchenbigpen1/normies/brainstorming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00019 | $0.01021 |
| Opus 5 | $0.00010 | $0.00511 |
| Sonnet 5 | $0.00004 | $0.00204 |
| Haiku 4.5 | $0.00002 | $0.00102 |
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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming Ideas Into Designs
Overview
Help turn ideas into fully formed designs through natural conversation. Your job is to understand the problem deeply before proposing any solution.
Before jumping to design, follow the system prompt's Solution-First Thinking — consider whether an existing tool, automation platform, or simple configuration change solves the problem before proposing custom work.
Understanding the Idea (Depth-First Questioning)
The system prompt covers the basics (one question per message, explore approaches, present design). This skill adds the questioning methodology that makes the difference between a good design and a great one.
How to think about what to ask
After every answer the user gives, pause and consider:
- What did that answer reveal that I didn't know before?
- What did it imply that I should dig deeper on?
- Could I explain their situation to someone else right now — or are there still parts I'd be guessing about?
Follow the thread. If someone says "we cold call leads we buy from a vendor," don't jump to asking about their tech stack. Ask about the leads — where do they come from? How good are they? What happens after the call? Stay on a topic until you actually understand it, then move on.
Push past surface-level answers. If someone says "we want to automate our outreach," that's not enough to design anything. What does outreach look like today? Who does it? What channels? What triggers it? Ask the follow-up that turns a vague statement into something concrete.
Your internal readiness test
You're NOT ready to design until you can clearly describe all of these to yourself:
- Their current reality — What do they do today, step by step? What tools do they use? What's manual, what's automated? Where does it break down?
- The desired outcome — What does "working" look like? Not features — results. What changes for them when this is done?
- The people involved — Who does what? Who provides input, who takes action, who sees the output?
- The information flow — What data is involved? Where does it come from? Where does it need to go? What format is it in?
- The rules and logic — What decisions get made along the way? What are the edge cases or exceptions? What does "it depends" depend on?
- The constraints — Budget, timeline, existing tools that must stay, team capabilities, dealbreakers.
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.
- 10d ago First seen · 84 lines · 19 tokens per session scan A 01386a95c801
brainstorming is a skill published in the GitHub repository yuchenbigpen1/normies (4 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,021 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.
Other skills, from other repositories
[object Object]
Skill "[object Object]" from microsoft/apm, covering what this package does, getting started, available primitives and included workflows.
apm-usage
Activate when the user asks about APM (Agent Package Manager): installing, configuring, authoring, or troubleshooting AI-agent packages, dependencies, compilation, MCP servers, policy, or any apm CLI command.
frontend-state-management
SocialApp user frontend state management — TanStack Query, Zustand, IndexedDB persistence, cache invalidation, multi-account isolation.
dev-orchestrator
Full-stack development orchestrator -- always-on, 16 phases (0-15): read-docs -> understand -> architect -> pseudocode -> plan -> contract -> validate -> implement -> evaluate -> verify -> test -> goals -> review -> critic -> document -> report.
bot-reviewer
Review chat bot code (Telegram, Discord, Slack) for callback safety, state machines, rate limits, and production readiness.
writing-hooks
How to write Claude Code hooks — lifecycle events, exit codes, profiles, jq/node parsing, settings.json wiring, and testing.