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 agentmods add skills/wsauret/flywheel/brainstormnpx skills add wsauret/flywheel --skill brainstormgit clone --depth 1 https://github.com/wsauret/flywheelWrote 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/wsauret/flywheel/brainstorm)<a href="https://agentmods.dev/skills/wsauret/flywheel/brainstorm"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/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 | $0.00058 | $0.01395 |
| Opus 5 | $0.00029 | $0.00698 |
| Sonnet 5 | $0.00012 | $0.00279 |
| Haiku 4.5 | $0.00006 | $0.00139 |
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 4d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming Skill
Transform ideas into validated designs through natural collaborative dialogue. Output is a design document for the planning skill.
Core Philosophy: Interactive Design
Never write the full design in one shot. Iterate through dialogue, not monologue.
| Checkpoint | Prevents |
|---|---|
| Research validation | Building on wrong assumptions |
| Understanding confirmation | Solving wrong problem |
| Approach selection | Pursuing suboptimal path |
| Design validation | Shipping wrong design |
"A bad line of research could lead to thousands of bad lines of code."
Anti-patterns:
- Dumping research findings on user (present insights, not data)
- Asking multiple questions at once (one at a time)
- Skipping approach exploration (always present 2-3 options)
- Presenting design without incremental validation
- Writing full design then asking "does this look good?"
Input
Feature idea via $ARGUMENTS. If empty, ask: "What would you like to explore?"
Phase 1: Silent Research
Run research agents to understand context. BLOCKING: DO NOT present findings to user -- use them to ask smarter questions.
Read references/research-dispatch.md before proceeding -- contains locator/analyzer dispatch templates and extraction checklist.
Run locators in parallel (codebase, patterns, docs, web), then analyze top findings for existing patterns, constraints, and conventions.
Phase 2: Research Review -- CHECKPOINT
HIGH LEVERAGE checkpoint. Bad research leads to bad design leads to thousands of bad lines of code.
Read references/research-dispatch.md before proceeding -- contains the presentation format and AskUserQuestion options.
Present a concise research summary (scope, key files, patterns, concerns). AskUserQuestion to approve, add focus, or redirect. Maximum 2 re-research cycles.
Phase 3: Understand the Idea
Ask questions one at a time to refine the idea.
Rules:
- One question per message
- Prefer multiple choice (AskUserQuestion with 2-4 options)
- Lead with recommendation
- YAGNI ruthlessly -- challenge scope creep
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.
- 4d ago First seen · 185 lines · 58 tokens per session scan A 69ace83a0b29
brainstorm is a skill published in the GitHub repository wsauret/flywheel (14 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,395 once invoked, about $0.0003 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
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
best-of-n
Generate a small set of independent candidate solutions in worktrees, judge them against one explicit rubric, and apply the winner only after PASS verification.
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale Pod runs and workers.
handoff
Write a compact, decision-ready handoff so the next session (or the user) can continue without reconstructing the current one. Use when the session is ending, context is running low, the user asks for a handoff / "pass the baton" / "hand off", or a long-running operation needs a durable state checkpoint.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.