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 agentmods add skills/jackfranklin/dotfiles/grill-menpx skills add jackfranklin/dotfiles --skill grill-megit clone --depth 1 https://github.com/jackfranklin/dotfilesWrote 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/jackfranklin/dotfiles/grill-me)<a href="https://agentmods.dev/skills/jackfranklin/dotfiles/grill-me"><img src="https://agentmods.dev/badge/skills/jackfranklin/dotfiles/grill-me.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.00406 |
| Opus 5 | $0.00024 | $0.00203 |
| Sonnet 5 | $0.00010 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00041 |
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 5d 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.
What it actually says
Choose the Interview Mode
Before asking substantive questions, determine whether the user wants Discovery or Refinement mode. If their request makes the mode clear, proceed without asking; otherwise, ask them to choose:
- Discovery mode — use when the user is uncertain about the problem or wants to explore alternatives. Interview them relentlessly about the plan, explore viable design branches, resolve dependencies one by one, and provide a recommended answer for each question.
- Refinement mode — use when the user has a bug report, issue, or mini-spec and wants to make it implementable. Treat the stated requirements as a strict boundary. Ask only questions needed to remove ambiguity, verify correctness, or choose among solutions that satisfy the stated scope. Prefer the smallest understandable solution and existing patterns over new abstractions or subsystems. Do not introduce adjacent features, cleanup, generalization, or speculative future-proofing; identify those separately as out of scope if relevant.
Examples: “explore options” selects Discovery mode; “flesh out this bug/spec” selects Refinement mode.
Ask questions one at a time. In either mode, stop when the user has a clear, bounded direction; do not continue exploring merely for completeness.
If a question can be answered by exploring the codebase, explore the codebase instead.
Repository glossary: At the start of the session, check whether .jai/glossary.md exists in the current repository. If it does, read it and use it as context. It is a stable glossary of canonical repository terminology and concepts, not a record of plan decisions, open questions, or this session's outcomes. Do not modify it during a grilling session.
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.
- 5d ago First seen · 21 lines · 49 tokens per session scan A d07f0513f646
grill-me is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 406 once invoked, about $0.0002 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 2026-08-30.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…