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 ivy00johns/Skill-Madness --skill find-unknownsgit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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/ivy00johns/skill-madness/find-unknowns)<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/find-unknowns"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/find-unknowns/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/ivy00johns/skill-madness/find-unknowns"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/find-unknowns.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 | $0.00210 | $0.02011 |
| Opus 5 | $0.00105 | $0.01006 |
| Sonnet 5 | $0.00042 | $0.00402 |
| Haiku 4.5 | $0.00021 | $0.00201 |
Grade A, and why
find-unknowns 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 9d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
find-unknowns
The map is not the territory. Your prompt, your plan, your mental model — that's the map. The codebase, the domain, the real constraints — that's the territory. The gap between them is your unknowns, and on a capable model the work is bottlenecked less by the model's ability and more by your ability to surface those unknowns before they get expensive. Every explainer, brainstorm, interview, and quiz is a cheap way to find out what you didn't know — before it costs you a bad implementation to find out the hard way.
Name the four unknowns
When you bring a problem, it breaks down four ways. Naming which kind you're short on tells you which move to reach for:
| Quadrant | What it is | Cheapest way to surface it |
|---|---|---|
| Known knowns | What you put in the prompt | Already written down |
| Known unknowns | What you know you haven't figured out | An interview → grill-me |
| Unknown knowns | So obvious you'd never write it, but you'd know it on sight | A brainstorm / prototype to react to |
| Unknown unknowns | What you haven't considered at all — you don't even know the question | A blindspot pass (this skill) |
The dangerous quadrant is the last one: you can't ask about what you don't know exists, and it's the one that surfaces late, deep in implementation, when reverting is expensive. That's the gap this skill is built to close.
What this skill owns vs. routes
This skill owns the two ends of the "do I actually understand this?" question — the before (blindspot pass) and the after (comprehension quiz). The middle of the lifecycle is already well-covered; route to the owner rather than re-doing it here:
| You want to… | Go to |
|---|---|
| Be interviewed on decisions you already have opinions about | grill-me |
| Generate directions / a throwaway prototype to react to | superpowers:brainstorming, ui-brief, claude-design-brief |
| Turn resolved decisions into a plan (leading with what's most likely to change) | plan-builder |
| Log deviations you hit mid-build so the next attempt learns | maintain-context |
| Deeply map an unfamiliar codebase | repo-deep-dive, zoom-out |
| Package the result into a pitch/explainer for buy-in | interactive-doc, artifact-publish |
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.
- 9d ago First seen · 156 lines · 210 tokens per session scan A b826864e32c3
find-unknowns is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed yesterday), licensed MIT. It adds 210 tokens to every session and 2,011 once invoked, about $0.0011 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…
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
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…