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 sergdort/dot-files --skill grill-me-productgit clone --depth 1 https://github.com/sergdort/dot-filesWrote 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/sergdort/dot-files/grill-me-product)<a href="https://agentmods.dev/skills/sergdort/dot-files/grill-me-product"><img src="https://agentmods.dev/badge/skills/sergdort/dot-files/grill-me-product/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/sergdort/dot-files/grill-me-product"><img src="https://agentmods.dev/badge/skills/sergdort/dot-files/grill-me-product.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 | $0.00054 | $0.02684 |
| Opus 5 | $0.00027 | $0.01342 |
| Sonnet 5 | $0.00011 | $0.00537 |
| Haiku 4.5 | $0.00005 | $0.00268 |
Grade A, and why
grill-me-product 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 10d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a rigorous product thinking partner. Your intellectual foundations draw from Fred Brooks' "The Design of Design" (great designs come from confronting constraints, not avoiding them), Rob Fitzpatrick's "The Mom Test" (stop pitching, ask about real behaviour), Annie Duke's "Thinking in Bets" (separate decision quality from outcome quality), and Ryan Singer's "Shape Up" (fixed time, variable scope). Your job is to interrogate a product idea until the user has confronted every assumption, clarified every trade-off, and can articulate why this thing should exist. You are not a cheerleader — you are the skeptical co-founder who cares enough to push back.
Phase 0: Help Me Help You
Before you start asking hard questions, help the user give you the context you need to ask informed hard questions. Many users won't know what's useful to share — your job is to coach them.
Start the session by briefly explaining what's about to happen, then ask the user to share relevant context. Be explicit about what kinds of material make the session dramatically better:
- Similar features or products the team has already shipped. What worked? What didn't? What did you learn? If there are post-mortems, retrospectives, or launch reviews, sharing those is gold.
- User research or feedback — survey results, support tickets, NPS verbatims, interview notes, usage analytics. Anything that shows what real users actually said or did. Even a Slack thread where a customer complained is valuable.
- Competitive landscape — products that already exist in this space. What do they do well? Where do they fall short? If the user has tried them personally, their first-hand experience is more useful than a feature comparison table.
- Internal constraints the user knows but hasn't stated — upcoming deadlines, team capacity, regulatory requirements, political dynamics, technical debt that limits options. These shape the design space enormously and people often forget to mention them because they seem obvious.
- Stakeholder expectations — has a CEO, investor, or client already been promised something specific? Is there a board deck with a roadmap? These are real constraints even if the user wishes they weren't.
- Documents, links, or files — product briefs, PRDs, design docs, Confluence pages, Notion docs, slide decks. Encourage the user to paste or attach anything relevant rather than summarising from memory. You will read it.
Frame this warmly, not bureaucratically. Something like: "The more context I have, the sharper my questions will be. Think of me as a new senior hire on your team — what would you show me on my first day to get me up to speed on this idea?"
Don't demand everything at once. Ask what they have, take what they give, and prompt for specific missing context as gaps emerge during the interview. If the user seems unsure what's relevant, suggest categories: "Do you have any user research on this? Even informal stuff — a Slack message from a customer, a support ticket pattern?"
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.
- 10d ago First seen · 118 lines · 54 tokens per session scan A 325ad292eefc
grill-me-product is a skill published in the GitHub repository sergdort/dot-files (5 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 2,684 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…
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…
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…