grill

grill is a skill for Claude Code, Codex from koolamusic/claudefiles. It costs 79 tokens per session (953 once invoked), scanned A, original, MIT.

A guided questioning method for examining a plan or shaping an unfinished idea. It either challenges assumptions and exposes gaps or helps narrow several options into a shared direction.

In plain words
What is it for?
Use it to stress-test an existing plan or design, or to work through requirements and solution choices when the direction is not settled.
Why use it?
It brings hidden risks, contradictions, and missing decisions to the surface before they become implementation problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Install

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.

agentmods
npx agentmods add skills/koolamusic/claudefiles/grill
Any agent
npx skills add koolamusic/claudefiles --skill grill
Clone the repo
git clone --depth 1 https://github.com/koolamusic/claudefiles

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for grill

README.md
[![agentmods](https://agentmods.dev/badge/skills/koolamusic/claudefiles/grill.svg)](https://agentmods.dev/skills/koolamusic/claudefiles/grill)
Your own site
<a href="https://agentmods.dev/skills/koolamusic/claudefiles/grill"><img src="https://agentmods.dev/badge/skills/koolamusic/claudefiles/grill.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 953 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.00953
Opus 5 $0.00039 $0.00477
Sonnet 5 $0.00016 $0.00191
Haiku 4.5 $0.00008 $0.00095

Measured 6d ago against content hash 6b46ac33a596, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

skills/grill/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grill

Relentless questioning that finds the gaps before code does. Two modes, one principle: reach shared understanding by walking every branch of the decision tree.

Pick the mode

Read the user's intent from context:

  • Stress-test (default) — a plan, design, or decision already exists. Your job is to attack it: surface risks, challenge assumptions, find contradictions, expose missing cases. You are the adversary.
  • Shape — no plan exists yet, or the user is exploring options. Your job is to co-create: propose 2-3 approaches with tradeoffs, iterate on requirements, narrow toward a decision. You are the collaborator.

If ambiguous, ask once: "Are we stress-testing something specific, or shaping the direction?"

Rules (both modes)

  1. One question at a time. Never batch. The user's answer to Q1 determines Q2.
  2. Provide your recommended answer alongside each question. The user can accept, reject, or redirect. Don't ask questions you could answer by reading the codebase — explore first, then ask what you genuinely don't know.
  3. Walk the decision tree depth-first. When a branch opens (e.g. "we'll use a queue"), follow it to its leaf (retry policy, dead-letter handling, monitoring) before moving to the next branch.
  4. Track resolved branches. Maintain a mental ledger. Never re-ask a settled question unless new information contradicts the answer.
  5. Flag when you're satisfied. When all branches resolve, say so explicitly. Present the final state as a compact summary of decisions.

Stress-test mode

Your stance is adversarial. For each aspect of the plan:

  • What breaks under load?
  • What breaks with bad input?
  • What's the failure mode and who notices?
  • What's the implicit assumption that nobody stated?
  • What's the dependency that isn't in the plan?
  • What happens when this interacts with the part three sections above?

Don't soften. If the plan has a hole, name it. If you tried to find a hole and couldn't, say "this part holds up" and move on — don't manufacture concerns.

Read the full file on GitHub · 94 lines

Changes

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.

  1. 6d ago First seen · 94 lines · 79 tokens per session scan A 6b46ac33a596

Subscribe to this mod's changes

grill is a skill published in the GitHub repository koolamusic/claudefiles (131 stars, last pushed 7d ago), licensed MIT. It adds 79 tokens to every session and 953 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens