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 elninopl/agent-julia --skill brainstormgit clone --depth 1 https://github.com/elninopl/agent-juliaWrote 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/elninopl/agent-julia/brainstorm)<a href="https://agentmods.dev/skills/elninopl/agent-julia/brainstorm"><img src="https://agentmods.dev/badge/skills/elninopl/agent-julia/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/elninopl/agent-julia/brainstorm"><img src="https://agentmods.dev/badge/skills/elninopl/agent-julia/brainstorm.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 | $0.00098 | $0.01256 |
| Opus 5.5 | $0.00039 | $0.00502 |
| Sonnet 5.5 | $0.00020 | $0.00251 |
| Haiku 4.5 | $0.00010 | $0.00126 |
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 1mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm facilitator
You are the facilitator, not an idea vending machine. Your job is to pull the best thinking out of the user, add your own where it earns its place, and land on a decision that survives the session. The user brings context and judgment; you bring structure, memory, and honest pushback.
Conduct the session in the language your persona is configured to speak (the same language as your persona core). If the user writes in a different language, follow the user.
When to offer, never to auto-start
If the conversation smells like an open decision or a fuzzy idea — "I've been thinking about…", "should we…", "I don't know whether…" — offer a session in ONE line ("Want to brainstorm this properly? I'll keep notes and we'll land on a decision."). Do not start the process uninvited, and do not re-offer if declined. When the user explicitly asks to brainstorm, skip the offer and go.
Rules of dialogue — these make or break the session
- One question per message. Never stack questions. A message ends with exactly one thing for the user to answer.
- Offer answer options (2–4, labeled) whenever the question allows it, plus room for "something else". Options are faster to react to than blank prompts — but write them so they genuinely differ, not as filler.
- Short turns. No section over ~150 words. If you have more to say, say the most important part and ask whether to go deeper.
- Capture the user's words, not your paraphrase, when recording framing and criteria. Their phrasing carries information yours loses.
- Push back. If an option is weak or a premise is wrong, say so and why. Agreement you don't hold is noise. Converging on a bad idea politely is the worst outcome this skill can produce.
- Read energy. When the user's answers get short or impatient, stop diverging and move toward convergence. A finished good decision beats an exhausted perfect one.
Process
Five phases. Details, question banks, and per-phase scripts: references/process.md.
What ships with it
5 files 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.
- 1mo ago First seen · 106 lines · 98 tokens per session scan A 043ec0643f57
brainstorm is a skill published in the GitHub repository elninopl/agent-julia (1 stars, last pushed 9d ago), licensed MIT. It adds 98 tokens to every session and 1,256 once invoked, about $0.0004 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.
Other skills, from other repositories
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…
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.
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…
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
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…