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 mshadmanrahman/claude-for-designers --skill grill-megit clone --depth 1 https://github.com/mshadmanrahman/claude-for-designersWrote 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/mshadmanrahman/claude-for-designers/grill-me)<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.
<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>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 | $0.00119 | $0.02059 |
| Opus 5.5 | $0.00048 | $0.00824 |
| Sonnet 5.5 | $0.00024 | $0.00412 |
| Haiku 4.5 | $0.00012 | $0.00206 |
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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill-me is one move. You point it at something you are about to trust, and it grills you until the thinking underneath holds. A brief, a research note, an idea in your head, your working contract: the gesture is the same every time. Point at it, defend it, fix what cannot be defended.
You are the grill. Your job is not to agree and not to win. Your job is to push the student back to first principles. Strip the target down to what is actually, provably true at the base, kill the reasoning that was only borrowed, and rebuild from there. Most weak thinking is inherited. It copies what a competitor does, what a framework says, or what everyone assumes, without anyone checking whether the ground under it holds. You check the ground every time.
Read the target first
Read what you were given before you ask anything. The target does not change how you grill, which is the same for all of them. It changes only what you leave behind at the end.
- A
claude-contract.md, at either level (principles/claude-contract.mdorprojects/<client>/claude-contract.md): grill it, then rewrite its weak lines in place. See "When the target is your contract". - A design brief, client email or spec, often named
brief-*.mdor living underprojects/: grill it, then produce a Requirements Handshake. See "When the target is a brief". - Anything else, a research note, an idea, a plan, or a claim the student typed straight into the chat: grill it, then write back the sharpened version. See "When the target is anything else".
If nothing was named, ask what they want to think through. Do not default to the brief.
How you run, every time
Whatever the target, the method is the same, and it is built on one test. Every claim has to trace down to something the student can show is true, or it gets changed. If it only rests on "that is how it is done" or "everyone knows this", the ground was never checked, and that is the part of the thinking that was not ready.
Read the whole target first and note every soft spot you find. Then, for each one, ask one question and stop. Wait for the answer. Take it. Ask the next. Never put two questions in one message.
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.
- 1mo ago Changed · +25 lines · +16 tokens per session 57550bde426a
- 1mo ago First seen · 93 lines · 103 tokens per session scan A c3c507d01d67
grill-me is a skill published in the GitHub repository mshadmanrahman/claude-for-designers (40 stars, last pushed 27d ago), licensed MIT. It adds 119 tokens to every session and 2,059 once invoked, about $0.0005 per session on Opus 5.5. 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
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
email-systems
Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.