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/emaballarin/ccplugins/grillnpx skills add emaballarin/ccplugins --skill grillgit clone --depth 1 https://github.com/emaballarin/ccpluginsWhat 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 | $0.00030 | $0.01494 |
| Opus 5 | $0.00015 | $0.00747 |
| Sonnet 5 | $0.00006 | $0.00299 |
| Haiku 4.5 | $0.00003 | $0.00149 |
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 yesterday.
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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ws:grill — interview a plan until nothing is assumed
Interview relentlessly until you and the operator reach a shared understanding of what is being built. Map the subject as a design tree: every decision branches into the decisions that hang off it.
This skill produces understanding, not artifacts. It writes nothing, changes nothing, and does not begin the work. It ends by handing off.
The frontier
The frontier is every decision whose prerequisites are already settled — the questions answerable now, without guessing at answers you have not heard yet. A question whose answer depends on another question still open in this round belongs to a later round, not this one.
Work the tree in rounds. Each round asks the whole frontier, then waits.
The round
1. Compute the frontier, and write it down
Recompute the frontier from everything settled so far, and state its size before anything else: "Frontier this round: 6 questions."
The frontier is fixed before a carrier is chosen. It is never trimmed, merged, or deferred to fit a display format. If the frontier does not fit the carrier, the carrier loses.
2. Ask the whole frontier, each question with a recommendation
Every question carries your recommended answer. A question without one is research you have not done yet — do it first.
❓ **Q1** — **<question title>**: <body; may be several paragraphs, may include
options>
➡️ <your recommended answer, and the one-line reason it is your recommendation>
3. Wait
Do not proceed to the next round, and do not begin any work, until the operator answers.
4. Recompute
Each round of answers reshapes the tree: settled decisions push the frontier outward and unblock what depended on them. Return to step 1.
Carrying a round
This rule governs grilling rounds only. It is a scoped specialisation, not a
general policy on AskUserQuestion — outside a round, and in every other skill,
the tool's own usage guidance applies unchanged.
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.
- yesterday First seen · 156 lines · 30 tokens per session scan A d648692f68de
grill is a skill published in the GitHub repository emaballarin/ccplugins (3 stars, last pushed 26d ago), licensed MIT. It adds 30 tokens to every session and 1,494 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 2026-08-31.
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…