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 exiao/pm-skills --skill quick-brainstormgit clone --depth 1 https://github.com/exiao/pm-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/exiao/pm-skills/quick-brainstorm)<a href="https://agentmods.dev/skills/exiao/pm-skills/quick-brainstorm"><img src="https://agentmods.dev/badge/skills/exiao/pm-skills/quick-brainstorm.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00512 |
| Opus 5 | $0.00022 | $0.00256 |
| Sonnet 5 | $0.00009 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
quick-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 7d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Brainstorm
Single-pass divergent thinking. No sub-agents, no heavy frameworks.
When the user gives you a question or problem, respond with:
-
5 distinct versions/approaches — each meaningfully different, not variations on a theme. For each, include:
- A short descriptive name
- 2-3 sentence explanation
- Estimated probability of success (as a %)
- Why this one might be the right pick
-
Key assumptions — State what assumptions you made that would significantly change your answer if they were false. These are the hidden beliefs your ranking rests on.
-
Your ranking — After all options and assumptions, state your preferred order with a one-line justification per option. The user wants your opinion, not just a menu.
Rules
- Keep it tight. No walls of text.
- Probabilities should sum to roughly 100% if the options are mutually exclusive, or can overlap if they're not.
- Be honest about uncertainty. If you don't know, say so.
- The assumptions section is the most valuable part. Don't phone it in.
Follow-up: JTBD narrowing
After brainstorming, if the user hasn't picked yet, offer to run a "jobs to be done" analysis on the options. Ask: "What are the jobs this [page/feature/system] needs to do?" Then score each brainstorm option against the jobs. This consistently surfaces the right pick faster than comparing options in the abstract. Especially powerful for UX/UI decisions where the glance-mode vs work-mode split determines what gets prime screen real estate.
- When brainstorming UX/design alternatives, each option should be a different paradigm (leaderboard vs kanban vs terminal log vs heatmap vs diff viewer), not variations on a theme (table with sidebar vs table without sidebar).
- When the user asks to "map out" or wireframe all options, render each as a full ASCII mockup with realistic data. Don't abbreviate. Users can't compare "a table" vs "a kanban" in prose; they need to see 30+ lines of ASCII showing exactly what each layout looks like with real column headers, data rows, and interactive elements.
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.
- 7d ago First seen · 34 lines · 44 tokens per session scan A 7a7ec8502f5f
quick-brainstorm is a skill published in the GitHub repository exiao/pm-skills (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 512 once invoked, about $0.0002 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
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…