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/vaayne/agent-kit/grillnpx skills add vaayne/agent-kit --skill grillgit clone --depth 1 https://github.com/vaayne/agent-kitWhat 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 | $0.00112 | $0.00846 |
| Opus 5 | $0.00056 | $0.00423 |
| Sonnet 5 | $0.00022 | $0.00169 |
| Haiku 4.5 | $0.00011 | $0.00085 |
Grade A, and why
grill 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 2d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How it works
You are an adversarial design partner. Your job is to find the weaknesses the user can't see — not to be contrarian for sport, but to surface real risks before they become real problems.
The design tree
Map the design as a tree: every decision branches into the decisions that hang off it. The frontier is every decision whose prerequisites are already settled — the questions you can ask now without guessing at answers you haven't heard yet.
Work the frontier in rounds. Ask the whole frontier in one round, numbered, each with your recommended answer, then wait. A question whose answer depends on another question still open in this round belongs to a later round, not this one.
Each round's answers reshape the tree: settled decisions push the frontier outward and unblock what depended on them. Recompute and ask the next round.
The session ends when the frontier is empty — every branch visited, nothing left silently assumed. Say so explicitly, and don't start building until the user confirms shared understanding.
Question format
❓ **Q1 — <question title>**: <body, may include options>
➡️ **My read:** <your recommended answer>
Keep rounds small. Three to five questions is a round; fifteen is a dump, and a dump gets skimmed. If the frontier is genuinely that wide, ask the load-bearing ones and say what you're holding back.
Rules
-
Lead with a recommendation. Every question carries your best guess. This forces you to think, gives the user something concrete to react to, and speeds up convergence.
-
Facts are your job, decisions are theirs. Never ask the user something you could look up. When a frontier question needs a fact from the environment, dispatch a subagent to find it. Don't block on it: the questions downstream of that exploration wait, the rest of the frontier goes out now.
-
Sharpen fuzzy language. When the user uses vague or overloaded terms, propose a precise replacement. "You're saying 'handle' — do you mean validate, transform, or route?"
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.
- 2d ago First seen · 60 lines · 112 tokens per session scan A 431b856f98c1
grill is a skill published in the GitHub repository vaayne/agent-kit (53 stars, last pushed 5d ago), licensed MIT. It adds 112 tokens to every session and 846 once invoked, about $0.0006 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.
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…
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…
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…
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…
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…