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 mhylle/claude-skills-collection --skill brainstormgit clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/mhylle/claude-skills-collection/brainstorm)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/brainstorm"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/brainstorm/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/mhylle/claude-skills-collection/brainstorm"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/brainstorm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.02849 |
| Opus 5 | $0.00044 | $0.01425 |
| Sonnet 5 | $0.00017 | $0.00570 |
| Haiku 4.5 | $0.00009 | $0.00285 |
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 11d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm
Overview
This skill provides structured single-session brainstorming through Socratic questioning and targeted analytical frameworks. It helps users refine raw ideas into well-structured concepts ready for implementation planning.
The key philosophy: adapt the analysis to the idea, not the idea to the analysis. Different types of ideas benefit from different frameworks. A risk-heavy initiative needs premortem analysis, not SCAMPER. A product feature needs SCAMPER, not just risk tables. Select the right tools for the job rather than running everything mechanically.
This skill runs in the main conversation, not a subagent. Phase 2 waits on the user's answers before continuing, and Phase 5 writes a file and offers follow-up skills — none of which a forked context can do, since it has no conversation history, gets backgrounded by default, and (under agent: Explore) has no write tools. Don't add context: fork or agent: to the frontmatter.
Initial Response
When this skill is invoked, don't use a canned response. Instead, acknowledge the user's idea naturally and start engaging immediately. If the user has already described their idea, summarize your understanding and begin asking clarifying questions. If they haven't, ask them to share what they're thinking about.
Avoid scripted openings like "I'm ready to help you explore and refine your idea." Just start the conversation.
Workflow (5 Phases)
Phase 1: Idea Capture & Classification
Parse the user's initial idea/concept and identify:
| Element | Description |
|---|---|
| Core Concept | The fundamental idea being proposed |
| Stated Goals | What the user explicitly wants to achieve |
| Implied Constraints | Limitations mentioned or implied |
| Project Context | Whether this relates to an existing codebase |
| Idea Type | Classification (see below) |
Idea Type Classification — Classify the idea to guide framework selection later:
| Type | Signals | Example |
|---|---|---|
| Product/Feature | New feature, UX change, user-facing capability | "Add a dashboard for metrics" |
| Architecture/Technical | System design, refactoring, infrastructure | "Migrate to microservices" |
| Strategy/Business | Market approach, pricing, partnerships | "Enter the enterprise segment" |
| Process/Workflow | How work gets done, tooling, automation | "Automate our deploy pipeline" |
| Creative/Open | Vague idea, exploration, "what if" | "What if we made it social?" |
| Risk/Problem | Something's broken, risky, or concerning | "Our auth system worries me" |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 292 lines · 87 tokens per session scan A 4353818a30f0
brainstorm is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 8d ago), licensed MIT. It adds 87 tokens to every session and 2,849 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…