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 Tx1207/hello-scholar --skill grillinggit clone --depth 1 https://github.com/Tx1207/hello-scholarWrote 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/tx1207/hello-scholar/grilling)<a href="https://agentmods.dev/skills/tx1207/hello-scholar/grilling"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/grilling/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/tx1207/hello-scholar/grilling"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/grilling.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 | $0.00053 | $0.00729 |
| Opus 5.5 | $0.00021 | $0.00292 |
| Sonnet 5.5 | $0.00011 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
grilling 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 4d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grilling
Help the user make a defensible choice by finding the uncertainty that matters most. Work from the desired outcome: a proposed tool, feature, or experiment may be a means rather than the goal. Distinguish observed facts, real constraints, preferences, and assumptions inherited from the first proposal.
Find the decision that changes the approach
Establish factual context from the supplied material and available files or tools. Ask the user for choices they own or facts you cannot obtain. Trace dependencies between decisions: settle the prerequisite before asking about consequences that depend on it. Prioritize a question by how much its answer could change the recommendation, scope, or success criteria, rather than by how easy it is to ask.
For each unresolved assumption, consider what would follow if it were false. Use a concrete alternative, counterexample, or failure condition to expose a meaningful tradeoff. Challenge the reasoning without requiring the user to defend a preference as an objective fact. When project evidence already resolves a question, state the finding and move on.
Question and update
Each round, ask one direct question whose prerequisites are known. Briefly explain why it changes the choice; offer a recommendation and its main tradeoff when the available evidence supports one. Use concise, mutually exclusive options when they make the decision easier. Do not invent a recommendation for an unknown personal preference.
Use the answer to revise the emerging decision and select the next question. Do not reopen an answered distinction without new conflicting evidence. When useful, state the implication immediately: which approach is now viable, ruled out, or still uncertain, and why. This keeps the user from having to reconstruct the reasoning at the end.
Stop when remaining answers would not change the choice, implementation, or acceptance; when the user asks to stop; or when a necessary fact cannot be obtained. In the last case, identify what depends on that fact and what can still proceed. Do not exhaust hypothetical future branches or force a final confirmation round.
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.
- 4d ago Changed c723bceb6194
- 9d ago Changed · +25 lines · +25 tokens per session 95bd586d4246
- 1mo ago Changed · -15 lines · -10 tokens per session 593a7a25115a
- 2mo ago First seen · 30 lines · 38 tokens per session scan A 1dcb0d460d27
grilling is a skill published in the GitHub repository Tx1207/hello-scholar (10 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 729 once invoked, about $0.0002 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…