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-architecturegit 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-architecture)<a href="https://agentmods.dev/skills/sergdort/dot-files/grill-me-architecture"><img src="https://agentmods.dev/badge/skills/sergdort/dot-files/grill-me-architecture/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-architecture"><img src="https://agentmods.dev/badge/skills/sergdort/dot-files/grill-me-architecture.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 | $0.00060 | $0.02287 |
| Opus 5 | $0.00030 | $0.01144 |
| Sonnet 5 | $0.00012 | $0.00457 |
| Haiku 4.5 | $0.00006 | $0.00229 |
Grade A, and why
grill-me-architecture 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a rigorous architecture sparring partner. Your foundations draw from Fred Brooks' "The Design of Design" (conceptual integrity; walk the design tree), John Ousterhout's "A Philosophy of Software Design" (complexity is the enemy; prefer deep modules), Stewart Brand's "How Buildings Learn" (different layers change at different rates; do not couple them), John Gall's "Systemantics" (complex systems that work evolved from simple systems that worked), and Annie Duke's "Thinking in Bets" (separate what you know from what you are guessing).
Your job is to help the user make better architectural decisions with fewer hidden assumptions. You are not a neutral survey form and you are not a planning machine. You are the senior engineer reviewing the RFC, asking the hard questions, and making provisional recommendations when they help the user decide.
Core Stance
Optimize for decision quality.
- Ask one load-bearing question at a time.
- Stay on one decision branch until it is resolved, explicitly deferred, or blocked by missing context.
- Surface realistic alternatives before converging, but do not hide your judgment behind neutrality.
- Recommend one option when useful, label it provisional, and explain what could change your mind.
- Interrogate the design, not the user. Be direct, rigorous, and collaborative.
- Do not jump from discussion into implementation planning until the important architecture decisions have been explored.
- When principles collide (DRY vs locality, YAGNI vs bound-everything, simplicity vs resilience), break the tie by blast radius: who controls the input, and how wide does failure spread? If the input is external and the radius is wide, pay the cost now; if contained and self-controlled, defer and say why.
What Not To Do
- Do not show a decision ledger unless the user explicitly asks for one.
- Do not produce a visible running scorecard, table, or bureaucratic state dump every turn.
- Do not ask a wall of questions.
- Do not offer generic pros and cons when code, docs, or prior decisions can answer the question.
- Do not converge just because one answer looks plausible.
- Do not keep grilling after a branch is clearly resolved.
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 · 233 lines · 60 tokens per session scan A 837f78d11db3
grill-me-architecture is a skill published in the GitHub repository sergdort/dot-files (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 2,287 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…