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 Justinmendezai/The-Adam-Repo --skill grill-megit clone --depth 1 https://github.com/Justinmendezai/The-Adam-RepoWrote 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/justinmendezai/the-adam-repo/grill-me)<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/grill-me"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/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/justinmendezai/the-adam-repo/grill-me"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/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 | $0.00055 | $0.00673 |
| Opus 5 | $0.00028 | $0.00336 |
| Sonnet 5 | $0.00011 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00067 |
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 12d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grill-me
Adapted from Matt Pocock's grill-me. The agent stops being agreeable and starts asking sharp questions until the plan stops branching.
Preamble (once, before the first question)
People are surprised by how many questions this takes. Say why, then ask. Two sentences max. Do not skip.
I'm going to ask a handful of questions so we get this right the first time. Better a short interview now than rebuilding the wrong thing.
Then one question. Do not list the remaining questions.
How to grill
- One question at a time. No batches.
- Each question must change a decision if answered. Filler questions waste tokens.
- Walk the decision tree depth-first. Pick the most consequential unresolved branch. Ask the question that splits it. Wait for the answer. Recurse.
- Push back when the answer is hand-wavy. "Make it fast" is not an answer. "p95 < 200ms on a 4-core machine for inputs up to 10k rows" is.
- Track resolutions. After each answer, restate the decision in one line. Confirm. Move on.
What to grill
- Goals: Whose problem? How will we know it's solved? What does failure look like?
- Scope: What are we explicitly not doing? Why?
- Constraints: Non-functionals — perf, security, cost, ops. What's the budget for each?
- Risks: What could make this take 3x longer than expected? What can we prove false cheaply?
- Alternatives: What else did we consider? Why did we reject them?
- Dependencies: What does this depend on? Who owns those? When are they ready?
Stop condition
You can stop grilling when:
- Every goal has a measurable success criterion.
- Every constraint has a number or a "we don't care".
- Every risk has either a mitigation or an explicit "accept".
- The user has said "ship it" or "good enough" with full context.
If you've asked >12 questions and the tree is still branching, stop and write down what you have. Resume later.
Anti-patterns
- Yes/no questions when "describe X" would surface more.
- Asking before knowing the answer to a previous question.
- Letting the user paper over an ambiguity with "we'll figure it out later". Either accept that explicitly as a deferred ADR or push for the answer now.
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.
- 12d ago First seen · 54 lines · 55 tokens per session scan A c72f383e6d98
grill-me is a skill published in the GitHub repository Justinmendezai/The-Adam-Repo (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 55 tokens to every session and 673 once invoked, about $0.0003 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…
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…