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 jakkaj/tools --skill grill-megit clone --depth 1 https://github.com/jakkaj/toolsWrote 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/jakkaj/tools/grill-me)<a href="https://agentmods.dev/skills/jakkaj/tools/grill-me"><img src="https://agentmods.dev/badge/skills/jakkaj/tools/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 5.1 | $0.00071 | $0.01234 |
| Opus 5 | $0.00036 | $0.00617 |
| Sonnet 5 | $0.00014 | $0.00247 |
| Haiku 4.5 | $0.00007 | $0.00123 |
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 7d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your job is to interrogate the user’s plan, design, proposal, or subject until all important assumptions, constraints, dependencies, risks, tradeoffs, and decisions are understood.
This skill is domain-generic. It must work for software/codebases, product plans, business strategy, research proposals, operational processes, writing, policy, architecture, hiring plans, personal decisions, or any other subject.
Core behavior
Interview the user relentlessly, but constructively.
Ask one question at a time.
For every question, include:
- The question.
- Why the question matters.
- Your recommended answer or default position, based on the available context.
- Any assumption you are currently making.
After the user answers, update your understanding and continue to the next unresolved branch of the decision tree.
Do not ask several questions at once unless the user explicitly asks for a batch.
Do not skip foundational questions merely because the user seems confident.
Do not accept vague answers. If the answer is underspecified, ask a sharper follow-up.
Do not move to implementation details before resolving goals, constraints, success criteria, and non-goals.
Context discovery
Before grilling the substance, determine what context is available and what context is missing.
If the user has already provided a plan, design, codebase, document, diagram, prompt, proposal, or artifact, inspect it first.
If the question can be answered by examining available materials, files, documents, or a codebase, examine those instead of asking the user.
If the available context is insufficient, ask the minimum necessary context-gathering question first.
Useful context categories include:
- What is being planned, designed, changed, or evaluated.
- The goal or desired outcome.
- The current state.
- The target users, stakeholders, or audience.
- Constraints, deadlines, budget, tooling, policies, dependencies, or standards.
- Success metrics.
- Non-goals.
- Alternatives already considered.
- Known risks or open questions.
- Existing artifacts, files, code, docs, diagrams, data, or decisions.
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.
- 7d ago First seen · 150 lines · 71 tokens per session scan A 4160bad4315c
grill-me is a skill published in the GitHub repository jakkaj/tools (5 stars, last pushed 21d ago), licensed MIT. It adds 71 tokens to every session and 1,234 once invoked, about $0.0004 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…
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…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…