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 team-attention/plugins-for-claude-natives --skill unknowngit clone --depth 1 https://github.com/team-attention/plugins-for-claude-nativesWrote 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/team-attention/plugins-for-claude-natives/unknown)<a href="https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/unknown"><img src="https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/unknown.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00138 | $0.01631 |
| Opus 5 | $0.00069 | $0.00816 |
| Sonnet 5 | $0.00028 | $0.00326 |
| Haiku 4.5 | $0.00014 | $0.00163 |
Grade A, and why
unknown 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unknown: Surface Blind Spots with Known/Unknown Quadrants
Surface hidden assumptions and blind spots in any strategy, plan, or decision using the Known/Unknown quadrant framework and hypothesis-driven questioning.
When to Use
- Strategy or planning documents that need scrutiny
- Decisions with unclear direction or hidden assumptions
- Any situation where "what we don't know" matters more than "what we do know"
For specific requirement clarification (feature requests, bug reports), use the vague skill. For content-vs-form reframing (optimizing within a form vs inventing a new form), use the metamedium skill.
Core Principle: Hypothesis-as-Options
ALWAYS use the AskUserQuestion tool for every question in R1/R2/R3 — never ask questions in plain text. The structured format enforces hypothesis-as-options and limits choice fatigue.
Present hypotheses as options instead of open questions. The hypotheses ARE the analysis — by designing good options, 80% of the analytical work is done before the user even answers. The user's job is to confirm, correct, or surprise.
BAD: "Why can't you do video content?" ← open question, high load
GOOD: "Time / Skill gap / No guests / High bar" ← pick one or more
- Each option IS a testable hypothesis about the user's situation
- Use multiSelect: true to catch compound causes
- "Other" is always available for out-of-frame answers
3-Round Depth Pattern
| Round | Purpose | Questions | Key trait |
|---|---|---|---|
| R1 | Validate draft quadrant | 3-4 | Broad, covers all quadrants |
| R2 | Drill into weak spots | 2-3 | Targeted, follows R1 answers |
| R3 | Nail execution details | 2-3 | Specific, optional |
Critical: Generate Round N questions from Round N-1 answers. Never use pre-prepared questions across rounds. Cap total at 7-10 questions.
Protocol
Phase 1: Intake
File provided: Read and extract goals, components, implicit assumptions, missing elements.
What ships with it
2 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.
- 9d ago First seen · 144 lines · 138 tokens per session scan A bbe9dbee1a1e
unknown is a skill published in the GitHub repository team-attention/plugins-for-claude-natives (824 stars, last pushed 4mo ago), licensed MIT. It adds 138 tokens to every session and 1,631 once invoked, about $0.0007 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…