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 vnnkl/agentflywheel --skill idea-wizardgit clone --depth 1 https://github.com/vnnkl/agentflywheelWrote 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/vnnkl/agentflywheel/idea-wizard)<a href="https://agentmods.dev/skills/vnnkl/agentflywheel/idea-wizard"><img src="https://agentmods.dev/badge/skills/vnnkl/agentflywheel/idea-wizard/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/vnnkl/agentflywheel/idea-wizard"><img src="https://agentmods.dev/badge/skills/vnnkl/agentflywheel/idea-wizard.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 | $0.00142 | $0.02044 |
| Opus 5.5 | $0.00057 | $0.00818 |
| Sonnet 5.5 | $0.00028 | $0.00409 |
| Haiku 4.5 | $0.00014 | $0.00204 |
Grade A, and why
idea-wizard 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 2mo 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea-Wizard
A structured ideation pipeline that alternates between divergent thinking (generate many ideas) and convergent thinking (select the strongest) to produce high-quality feature ideas grounded in an existing codebase.
Why This Structure Matters
Unstructured brainstorming produces two failure modes:
-
Tunnel vision — jumping to the first decent idea and elaborating it without exploring alternatives. The result is a local optimum: a perfectly refined version of an idea that was never the best option.
-
Unfocused sprawl — generating dozens of ideas with no winnowing. Everything stays at surface level. Nothing gets developed enough to evaluate seriously.
The expansion/contraction pattern solves both problems. First you go wide (30 ideas) to escape tunnel vision. Then you go narrow (5 best) to identify the strongest themes. Then you re-expand around those themes (15 ideas) to explore the most promising directions at higher resolution. The human picks from a curated set that has been both broadly explored and deeply developed.
The specific ratios (30 → 5 → 15) are not arbitrary. 30 forces you past the obvious ideas that come first — the genuinely novel ones tend to appear after idea 15-20 when the easy options are exhausted. Winnowing to 5 creates real selection pressure and surfaces the underlying themes worth pursuing. Re-expanding to 15 around those 5 themes gives 3 variations per theme on average, which is enough to find the specific angle that fits the project best.
Process
Step 0: Understand the Project
Before generating ideas, build a mental model of the project. Read:
- Project root files (package.json, Cargo.toml, go.mod, etc.) to understand the stack
- README or docs for stated purpose and goals
- Directory structure to understand architecture
- Any existing task/issue files, TODO lists, or roadmap documents
- AGENTS.md or CLAUDE.md if present
Summarize the project back to the user in 3-5 sentences: what it does, who it serves, what stack it uses, and its current state (early prototype, production app, side project, etc.). Ask the user to correct anything wrong before proceeding.
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.
- 2mo ago First seen · 169 lines · 142 tokens per session scan A 3c77fed74426
idea-wizard is a skill published in the GitHub repository vnnkl/agentflywheel (2 stars, last pushed 5mo ago), licensed MIT. It adds 142 tokens to every session and 2,044 once invoked, about $0.0006 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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…