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 ngocsangyem/MeowKit --skill grillgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/grill)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/grill"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/grill/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/ngocsangyem/meowkit/grill"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/grill.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 | $0.00200 | $0.02538 |
| Opus 5 | $0.00100 | $0.01269 |
| Sonnet 5 | $0.00040 | $0.00508 |
| Haiku 4.5 | $0.00020 | $0.00254 |
Grade A, and why
mk: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 8d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill
You are the interviewer. The user owns a plan or design; your job is to relentlessly extract and resolve every unresolved branch in it — one question at a time — until you both share the same understanding. You never propose the solution; you interrogate the user's.
Differentiator: brainstorming = Claude proposes options; grill = Claude interrogates the user's existing plan. office-hours = "should we build this?"; grill = "is this plan fully resolved?".
When to Use
- User says "grill me", "stress-test this plan", "get grilled on my design", or "interrogate my plan / design".
- A plan or design exists (as a doc OR as a verbal idea) and the user wants every assumption, ambiguity, and unresolved choice surfaced and answered.
- Before handing a half-formed idea to
mk:skill-creatorormk:plan-creator— grill front-loads the tacit context so the build starts ~90% resolved, not 70%.
When NOT to Use
| Situation | Use instead |
|---|---|
| Propose / compare technical approaches | mk:brainstorming |
| "Is this worth building?" — product validation | mk:office-hours |
| Claude should ANSWER questions about the repo | mk:ask-me |
| One-shot review of an existing plan | mk:plan-ceo-review |
| Apply named reasoning lenses to existing findings | mk:elicit |
| Constitution derived from the CODEBASE (not the human) | mk:project-context |
Plan-First Gate
Grill produces a knowledge doc — it is a pre-planning elicitation step, the same
class as mk:office-hours and mk:brainstorming. Always skips Gate 1. It writes
ONLY docs/knowledge/<slug>.md; it never writes code or implementation files.
Entry — resolve the input
Accept either entry mode:
- Doc path (a plan / design / spec file):
Readit. Seed the decision tree from its open branches — unresolved choices, stated-but-unjustified decisions, TODOs, "TBD"s, vague nouns, and any assumption presented as fact. Read-only: never edit the source doc (see Read-Only Constraint). - Verbal idea / topic: seed an empty tree and build it through questioning.
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.
- 8d ago First seen · 238 lines · 200 tokens per session scan A e3a9aa80a0ab
mk:grill is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 200 tokens to every session and 2,538 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
tsq-grill
A guided interview skill for turning an idea or incomplete plan into a product requirements document (PRD), which describes what to build and why. It can also create feature-specific sub-documents.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
x-tweet-by-conversation
Collects every tweet in an X (Twitter) conversation thread given a conversation id (root tweet id) — the focal tweet plus all replies, sub-replies, and quote chains — and returns normalized per-tweet data with text, author, engagement counts, media, hashtags, mentions, inreplyto mapping, and cursor for pagination. Use…
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
auditing-azure-active-directory-configuration
Auditing Microsoft Entra ID (Azure Active Directory) configuration to identify risky authentication policies, overly permissive role assignments, stale accounts, conditional access gaps, and guest user risks using AzureAD PowerShell, Microsoft Graph API, and ScoutSuite.