Borrowing it
Nothing to install: this file belongs to hachej/boring-ui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hachej/boring-ui/main/.agents/skill-references/plan/grill-for-unknowns/SKILL.mdgit clone --depth 1 https://github.com/hachej/boring-uiWrote 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/hachej/boring-ui/grill-for-unknowns)<a href="https://agentmods.dev/skills/hachej/boring-ui/grill-for-unknowns"><img src="https://agentmods.dev/badge/skills/hachej/boring-ui/grill-for-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/hachej/boring-ui/grill-for-unknowns"><img src="https://agentmods.dev/badge/skills/hachej/boring-ui/grill-for-unknowns.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00073 | $0.00712 |
| Opus 5 | $0.00036 | $0.00356 |
| Sonnet 5 | $0.00015 | $0.00142 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
grill-for-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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill for Unknowns
Adversarially review a plan/design to surface what nobody has considered yet. Inspired by nicobailon/grill-for-unknowns.
Worked example in this repo:
docs/issues/391/runtime-refactor/REVIEW-2026-07-11-unknowns.md.
Frame — four quadrants
Classify every gap before probing:
- Known-knowns — proven by code/docs. Cite, don't question.
- Known-unknowns — acknowledged open decisions. Track, don't rediscover.
- Unknown-knowns — you'd recognize the right answer but can't state it upfront (team memory not written into the plan). Surface and write down.
- Unknown-unknowns — nobody's considered it. The real target of this skill.
Seven blindspot lenses
Run each lens against the plan; example question shape for this repo's runtime/plan work:
- Scale — what happens under 10x workspace/session concurrency?
- Security — does the new boundary change what paths/tools an adapter can reach?
- Failure modes — if it crashes mid-operation, what state is inconsistent and who detects it?
- Edge cases — what happens to sessions/workspaces created under the old runtime still open at swap time?
- Concurrency — can two mode transitions race and leave a pair mismatched?
- Migration — what must exist in both old and new shapes simultaneously, and for how long?
- Rollback — if we revert, what is now irreversible (schema, on-disk format, deleted code path)?
Process
- Restate the plan and its stated assumptions.
- Read the actual code/tests — never trust the plan's self-description.
- Build an unknowns ledger sorted into the four quadrants.
- Run the seven lenses; rank suspects by implementation risk.
- Grill one material decision at a time.
- For low-risk gaps, propose a default instead of blocking.
- Stop when every unknown that could materially change the plan is resolved or explicitly accepted as an assumption.
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 · 65 lines · 73 tokens per session scan A cbf2da23a920
grill-for-unknowns is a skill published in the GitHub repository hachej/boring-ui (46 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 712 once invoked, about $0.0004 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…