grill-me

grill-me is a skill for Claude Code from mshadmanrahman/claude-for-designers. It costs 103 tokens per session (1,304 once invoked), scanned A, original, MIT.

A questioning process for improving either a Claude contract or a design brief. In contract mode it checks that every line is an enforceable rule; in brief mode it probes for missing or unclear requirements.

In plain words
What is it for?
Use it to review a contract line by line or challenge a brief until its goals, scope, and requirements are clear.
Why use it?
It exposes vague instructions and unanswered questions before they cause inconsistent work.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to review a contract line by line or challenge a brief until its goals, scope, and requirements are clear.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mshadmanrahman/claude-for-designers/grill-me
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.

Any agent
npx skills add mshadmanrahman/claude-for-designers --skill grill-me
Clone the repo
git clone --depth 1 https://github.com/mshadmanrahman/claude-for-designers

Made for: Claude Code.

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-me

README.md
[![agentmods](https://agentmods.dev/badge/skills/mshadmanrahman/claude-for-designers/grill-me/github.svg)](https://agentmods.dev/skills/mshadmanrahman/claude-for-designers/grill-me)
Your own site
<a href="https://agentmods.dev/skills/mshadmanrahman/claude-for-designers/grill-me"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claude-for-designers/grill-me/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.

agentmods 80×15 button for grill-me

Your own site · 80×15
<a href="https://agentmods.dev/skills/mshadmanrahman/claude-for-designers/grill-me"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claude-for-designers/grill-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,304 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00103 $0.01304
Opus 5 $0.00051 $0.00652
Sonnet 5 $0.00021 $0.00261
Haiku 4.5 $0.00010 $0.00130

Measured 11d ago against content hash c3c507d01d67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 11d 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.

.claude/skills/grill-me/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read the file you were pointed at before you ask anything. That file decides which mode you run.

  • The target is a claude-contract.md, at either level (principles/claude-contract.md or projects/<client>/claude-contract.md): run contract mode.
  • The target is anything else, a brief, a client email, a spec: run brief mode.

If no file was named, ask which file to run on. Do not send the student to the project brief instead. Both modes are real, and Class 2 runs this skill on the contract.


Contract mode

You are a skeptical senior designer reading someone's working contract. This is not a brief, so none of the brief questions further down apply here. Do not ask them.

One test runs this whole mode. Every line has to be a thing Claude must always do, or a thing Claude must never do. If Claude ignored the line, the student should be able to point at the output and say "there, you broke it". A line nobody could tell had been broken is a wish. A wish cannot be broken, so it cannot be followed either.

The four defects you hunt for

1. A wish, not a rule. "Be professional." "Give better answers." "Understand my style." Nobody can tell when these get ignored. Ask what the student would point at if Claude ignored the line. Then rewrite it as a thing Claude must always do, or a thing Claude must never do.

2. A line at the wrong level. Something about one client sitting in the root file, or something about the designer sitting in a project file. The test is one question: would this still be true on your next job, for a different client? Yes means the root file. No means the project file.

3. A contradiction. Two lines that pull against each other. "Keep every answer short" and "explain your full reasoning" is one. Claude picks one of them at random when this happens, and the student reads that randomness as Claude being unreliable.

4. A missing boundary. Nothing written down about what the student refuses to hand over. Every contract needs at least one line naming work that stays theirs.

Read the full file on GitHub · 93 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. 11d ago First seen · 93 lines · 103 tokens per session scan A c3c507d01d67

Subscribe to this mod's changes

grill-me is a skill published in the GitHub repository mshadmanrahman/claude-for-designers (28 stars, last pushed 19d ago), licensed MIT. It adds 103 tokens to every session and 1,304 once invoked, about $0.0005 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.