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 zhouyou-gu/skill-marketplace-template --skill finding-agent-unknownsgit clone --depth 1 https://github.com/zhouyou-gu/skill-marketplace-templateWrote 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/zhouyou-gu/skill-marketplace-template/finding-agent-unknowns)<a href="https://agentmods.dev/skills/zhouyou-gu/skill-marketplace-template/finding-agent-unknowns"><img src="https://agentmods.dev/badge/skills/zhouyou-gu/skill-marketplace-template/finding-agent-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/zhouyou-gu/skill-marketplace-template/finding-agent-unknowns"><img src="https://agentmods.dev/badge/skills/zhouyou-gu/skill-marketplace-template/finding-agent-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 | $0.00045 | $0.01210 |
| Opus 5 | $0.00023 | $0.00605 |
| Sonnet 5 | $0.00009 | $0.00242 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
finding-agent-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 11d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finding Agent Unknowns
Core Principle
The prompt is the map; the repo, user intent, and real-world constraints are the territory; unknowns are the gap. Reduce that gap before the work gets expensive.
Use this as a lightweight operating protocol, not as ceremony. If a task is trivial, deterministic, and already well-scoped, acknowledge that no unknowns pass is needed and proceed normally.
Unknown Buckets
- Known knowns: explicit requirements, constraints, files, APIs, tests, and acceptance criteria.
- Known unknowns: questions already visible to the user or agent.
- Unknown knowns: user taste, team conventions, and obvious-in-context expectations that have not been stated.
- Unknown unknowns: codebase constraints, domain pitfalls, better approaches, or failure modes nobody has named yet.
Workflow
Before Work
- Restate the task in one sentence.
- Inspect discoverable facts before asking the user: search the repo, read relevant docs, check schemas/types/configs, and identify existing patterns.
- Run a blindspot pass:
- What assumptions would change architecture, scope, data shape, UX, or verification?
- What existing code paths, policies, or external constraints could make the obvious approach wrong?
- What would a domain expert or project maintainer ask first?
- Separate outputs into:
- discovered facts with evidence sources
- assumptions safe to make
- high-impact questions for the user
- cheap artifacts to create before implementation
- Ask only questions that can change the solution or acceptance criteria. Do not ask for facts the environment can reveal.
- For taste-heavy work, make a small prototype, mock, sketch, or reference comparison before touching production code. Keep it response-local or in an ignored scratch path unless the user explicitly asks for a tracked artifact.
During Work
Maintain implementation notes when the task lasts more than a short edit or when the plan changes. Keep notes response-local by default. If a durable workspace contract already exists and current-state persistence is needed, write only to the contract's live-progress surface, such as AGENT_PROGRESS.md; never patch immutable or durable-policy files just to store transient unknowns. Track:
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.
- 11d ago First seen · 99 lines · 45 tokens per session scan A a78f5c397628
finding-agent-unknowns is a skill published in the GitHub repository zhouyou-gu/skill-marketplace-template (5 stars, last pushed 18d ago), licensed MIT. It adds 45 tokens to every session and 1,210 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…
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…