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 thienanblog/awesome-ai-agent-skills --skill brainstorm-firstgit clone --depth 1 https://github.com/thienanblog/awesome-ai-agent-skillsWrote 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/thienanblog/awesome-ai-agent-skills/brainstorm-first)<a href="https://agentmods.dev/skills/thienanblog/awesome-ai-agent-skills/brainstorm-first"><img src="https://agentmods.dev/badge/skills/thienanblog/awesome-ai-agent-skills/brainstorm-first/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/thienanblog/awesome-ai-agent-skills/brainstorm-first"><img src="https://agentmods.dev/badge/skills/thienanblog/awesome-ai-agent-skills/brainstorm-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 13 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00073 | $0.01733 |
| Opus 5 | $0.00036 | $0.00866 |
| Sonnet 5 | $0.00015 | $0.00347 |
| Haiku 4.5 | $0.00007 | $0.00173 |
Grade A, and why
brainstorm-first 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 12d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm First
Turn an uncertain request into a reality-checked decision before implementation. Preserve the user's goal, but do not endorse an impractical feature or preferred solution merely because the user proposed it.
Non-negotiable gates
- Do not change project or external state, make purchases, deploy, or take other implementation actions before the user chooses an option. Read-only discovery and safe diagnostic checks are allowed when they help clarify the decision. In UI/UX concept mode, temporary preview images explicitly requested for comparison are also allowed, but do not treat them as production assets or add them to the project before selection.
- Inspect available context before asking questions. Do not ask the user for facts that can be found safely in supplied artifacts, the repository, logs, configuration, or authoritative documentation.
- Do not silently assume a material product, architecture, behavior, scope, cost, or design choice. State unresolved material assumptions and ask about them.
- Challenge requirements when evidence, constraints, user value, accessibility, security, maintenance, compatibility, cost, or operational reality makes the current request weak. Explain the concrete issue and offer a better framing; do not be contrarian without evidence.
- Present exactly three meaningfully different, viable options and recommend one. Do not create cosmetic variants merely to reach three.
- Include the required scores and deductions in every completed decision package after the brief is decision-ready. Do not score an incomplete clarification turn. Scores are structured judgments, not measured facts; do not inflate them or imply false precision.
- After presenting the decision package, stop and wait for the user to choose, revise, or reject the options. Do not continue with the recommendation automatically.
Workflow
1. Route and investigate
Choose the mode that owns the uncertainty:
- Requirements: unclear scope, product behavior, architecture, workflow, or implementation direction.
- Diagnosis: a bug, failure, regression, or unexpected behavior whose cause is not yet established.
- UI/UX concepts: the user wants three visual interface directions before implementation.
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.
- 12d ago First seen · 144 lines · 73 tokens per session scan A 53209f10583c
brainstorm-first is a skill published in the GitHub repository thienanblog/awesome-ai-agent-skills (65 stars, last pushed 14d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,733 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…
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…