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 avivsinai/skills-marketplace --skill finding-unknownsgit clone --depth 1 https://github.com/avivsinai/skills-marketplaceWrote 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/avivsinai/skills-marketplace/finding-unknowns)<a href="https://agentmods.dev/skills/avivsinai/skills-marketplace/finding-unknowns"><img src="https://agentmods.dev/badge/skills/avivsinai/skills-marketplace/finding-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/avivsinai/skills-marketplace/finding-unknowns"><img src="https://agentmods.dev/badge/skills/avivsinai/skills-marketplace/finding-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 | $0.00184 | $0.01526 |
| Opus 5 | $0.00092 | $0.00763 |
| Sonnet 5 | $0.00037 | $0.00305 |
| Haiku 4.5 | $0.00018 | $0.00153 |
Grade A, and why
finding-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 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finding Unknowns
The map is not the territory. The prompt, the plan, and the context window are the map; the codebase, the domain, and the user's actual intent are the territory. The gap between them is the unknowns — and an unknown found before code is written costs minutes, while the same unknown found three PRs later costs the three PRs.
This skill is a guided conversation: the quadrant walk. Together with the user you fill in a four-quadrant map of the task, one quadrant per stage, and the user walks away holding the completed map. The map is the deliverable; implementation is a different task that starts only after the map is handed over.
Two moves apply at every stage:
- Reacting beats imagining — for tacit unknowns. When the unknown is taste, shape, vocabulary, or "I'll know it when I see it", never ask the user to describe what they want when you can hand them something concrete to react to — a rendered option, a clickable mock, a decisions table. Reacting extracts knowledge the user has but cannot articulate unprompted. When the unknown is a factual constraint or an architectural decision, ask the highest-blast-radius question directly, with a recommendation.
- Every artifact assembles the reply. End each artifact with the user's next message pre-drafted: steal/skip chips, resonate checkboxes, a decisions table, a copyable sharpened prompt — so their reaction becomes their next message with near-zero typing.
The Quadrant Walk
Five stages, walked in order, one at a time. When you enter a stage, read its reference file and follow it. Name the current quadrant as you go — the user should always know where they stand on the map — and finish the stage in front of you before opening the next.
What ships with it
6 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.
- 12d ago First seen · 105 lines · 184 tokens per session scan A de2c4576f156
finding-unknowns is a skill published in the GitHub repository avivsinai/skills-marketplace (2 stars, last pushed today), licensed MIT. It adds 184 tokens to every session and 1,526 once invoked, about $0.0009 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
a-rules-optimizer
Audit .claude/rules/ and CLAUDE.md against what the codebase actually does.
a-review-optimizer
Read this codebase and write, or sharpen, a review skill fitted to it.
a-review-core
Shared review engine that a project's own review skill reads. Not run on its own.
a-self-learner
Turn recurring review findings into proposed rule and skill updates.
smith
Scaffold a new Quickstop plugin with correct structure and conventions.
sanitize-public
Pre-publish privacy gate. Runs before anything crosses from a private working environment to a public one: a plugin marketplace repo, a downloadable bundle, a public GitHub repo or gist, a shared skill or command. Scans the exact files that will ship for key material, credentials, internal hostnames, LAN IPs, personal…