Borrowing it
Nothing to install: this file belongs to lsampaioweb/ai-instructions. 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/lsampaioweb/ai-instructions/main/.cursor/skills/grill-me/SKILL.mdgit clone --depth 1 https://github.com/lsampaioweb/ai-instructionsWrote 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/lsampaioweb/ai-instructions/grill-me)<a href="https://agentmods.dev/skills/lsampaioweb/ai-instructions/grill-me"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/grill-me/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/lsampaioweb/ai-instructions/grill-me"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/grill-me.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 | $0.00126 | $0.01351 |
| Opus 5.5 | $0.00050 | $0.00540 |
| Sonnet 5.5 | $0.00025 | $0.00270 |
| Haiku 4.5 | $0.00013 | $0.00135 |
Grade A, and why
grill-me 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 1mo 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill Me
Most build requests fail in specification, not execution. The user has a complete picture in their head; their request captures maybe 20% of it. Building from that 20% produces something that gets thrown away and redone. Ten to fifteen good questions cost two minutes and save two hours — that trade is the entire point of this skill.
Core rule
Before producing any code, file, design, or deliverable, conduct an interview totaling 10-15 questions. Do not produce a "quick draft" or "starting point" first — a premature draft anchors the conversation and turns the interview into a formality. The interview comes first, always, unless a project agent or an instruction contract already owns the questions. In that case, do not run this skill.
How to run the interview
Batch, don't barrage. Ask in 2-3 rounds of 4-6 questions rather than 15 at once. Round 1 establishes fundamentals (purpose, audience, scope). Rounds 2-3 drill into whatever the earlier answers revealed. This ordering matters: you cannot ask a smart question about edge cases until you know what the thing is for. Number the questions so the user can answer by number.
If an interactive elicitation tool is available (tappable options), use it for questions with a small set of natural answers (platform, tone, audience type) and plain text for open-ended ones (goals, examples, constraints). Mixing both keeps the interview fast for the user.
Never ask what you already know. Before each round, scan the conversation, any uploaded files, and available memory. Asking something the user already answered signals you weren't listening and wastes one of your limited question slots.
Every question must be able to change the build. Before asking a question, know what you would do differently for each plausible answer. If every answer leads to the same decision, cut the question and spend the slot on something that matters.
Adapt depth to stakes. A weekend hobby script earns 10 questions; a client-facing product earns 15. Stay inside the 10-15 band, but choose where in it deliberately.
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.
- 1mo ago Changed · +1 lines · -5 tokens per session 48d28fcd871a
- 1mo ago First seen · 112 lines · 131 tokens per session scan A 5c8c25bbd8d5
grill-me is a skill published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 5d ago), licensed MIT. It adds 126 tokens to every session and 1,351 once invoked, about $0.0005 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 2026-09-20.
grill-me compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| grill-melsampaioweb/ai-instructions | Skill | 1 | 5d ago | MIT | A | 126 | Cursor |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |