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 ericgandrade/claude-superskills --skill grill-megit clone --depth 1 https://github.com/ericgandrade/claude-superskillsWrote 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/ericgandrade/claude-superskills/grill-me)<a href="https://agentmods.dev/skills/ericgandrade/claude-superskills/grill-me"><img src="https://agentmods.dev/badge/skills/ericgandrade/claude-superskills/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/ericgandrade/claude-superskills/grill-me"><img src="https://agentmods.dev/badge/skills/ericgandrade/claude-superskills/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 | $0.00070 | $0.00806 |
| Opus 5 | $0.00035 | $0.00403 |
| Sonnet 5 | $0.00014 | $0.00161 |
| Haiku 4.5 | $0.00007 | $0.00081 |
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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill Me
Purpose
Stress-test a plan, design, or idea through relentless Socratic questioning. Walk down every branch of the decision tree, resolve dependencies between decisions one-by-one, and reach a shared understanding where no assumption is left unchallenged.
When to Use
Trigger ONLY when the user explicitly uses the word "grill" — e.g.:
- "grill me on this"
- "grill me on my plan / architecture / design"
- "I want you to grill me before I present"
- PT: "me grille sobre esse plano"
Do NOT trigger for synonyms or near-misses, even when the intent seems similar:
- "stress-test this" → not grill-me
- "poke holes in my plan" → not grill-me
- "play devil's advocate" → not grill-me
- "challenge my assumptions" → not grill-me
- "pressure-test this" → not grill-me
- "review this and tell me what's wrong" → not grill-me
- "give me feedback" → not grill-me
Workflow
Step 0 — Understand the Subject
Read the plan, design, or idea the user has provided. If working in a codebase, explore relevant files before asking questions that can be answered by reading the code.
Step 1 — Build the Decision Tree (silent)
Before asking the first question, mentally map:
- Core decisions already made (what's locked in)
- Branches that are open or unresolved
- Dependencies between decisions
- Unstated assumptions worth surfacing
Step 2 — Interview Relentlessly
Ask one question at a time. For each question:
- Ask the question
- Provide your recommended answer with brief reasoning
- Wait for the user's response before moving on
Work through branches systematically — exhaust one thread before opening another. When an answer reveals a new sub-question, follow it immediately.
Question types to cycle through:
- Scope: What's in? What's explicitly out?
- Dependencies: What does this depend on that isn't defined yet?
- Failure modes: What breaks first under load / edge cases / bad inputs?
- Alternatives rejected: Why this approach and not X?
- Success criteria: How will you know this worked?
- Reversibility: What's hard to undo? What's the rollback plan?
- Ownership: Who owns each part when something goes wrong?
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 86 lines · 70 tokens per session scan A 02d810c3616a
grill-me is a skill published in the GitHub repository ericgandrade/claude-superskills (75 stars, last pushed 4mo ago), licensed MIT. It adds 70 tokens to every session and 806 once invoked, about $0.0003 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.
Other skills, from other repositories
writing-fragments
Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate"…
obsidian-vault
Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…
writing-shape
Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants…