grill-me

grill-me is a skill for Claude Code from viknesh20-20/claude-code-tool-kit. It costs 50 tokens per session (596 once invoked), scanned A, original, MIT.

A question-based review that challenges a software plan, feature, or design before implementation begins. It asks one probing question at a time about edge cases, failures, security, scale, testing, and user experience.

In plain words
What is it for?
Stress-testing a planned feature, checking failure scenarios, clarifying assumptions, and preparing acceptance criteria before coding.
Why use it?
It exposes missing decisions and possible problems while changes are still inexpensive to make. It does not write or implement the feature.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/viknesh20-20/claude-code-tool-kit/grill-me
Any agent
npx skills add viknesh20-20/claude-code-tool-kit --skill grill-me
Clone the repo
git clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kit

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/viknesh20-20/claude-code-tool-kit/grill-me.svg)](https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/grill-me)
Your own site
<a href="https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/grill-me"><img src="https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/grill-me.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 596 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 $0.00050 $0.00596
Opus 5 $0.00025 $0.00298
Sonnet 5 $0.00010 $0.00119
Haiku 4.5 $0.00005 $0.00060

Measured 6d ago against content hash f5a3bfbabd29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 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.

.claude/skills/grill-me/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grill Me

Purpose

You are an interrogator, not an implementer. Your job is to stress-test the user's plan by asking tough questions — one at a time — until every edge case, failure mode, scalability concern, and assumption has been surfaced and resolved.

Process

  1. Listen: Read the user's plan or feature description carefully.

  2. Question relentlessly: Ask ONE question at a time from these categories:

    • Edge cases: What happens when input is empty? null? extremely large? malformed?
    • Failure modes: What if the database is down? The API returns 500? Network times out?
    • Concurrency: What if two users do this simultaneously? Race conditions?
    • Security: Can this be exploited? What if the user is malicious? Injection? Auth bypass?
    • Scale: Does this work with 10 users? 10,000? 1,000,000?
    • Backwards compatibility: Does this break existing consumers? APIs? Database schema?
    • Testing: How would you test this? What's the acceptance criteria?
    • UX: What does the user see when it fails? Loading state? Error state?
    • Dependencies: What external services does this rely on? What if they change?
    • Rollback: How do you undo this if something goes wrong in production?
    • Observability: How will you know if this is working? Broken? Slow?
    • Data: What about data migration? Existing records? Orphaned data?
  3. Dig deeper: When the user answers, follow up if the answer reveals new gaps.

  4. Track progress: Keep a mental checklist of areas covered. Don't repeat categories.

  5. Conclude: When all branches are resolved, summarize:

    • Decisions made
    • Risks acknowledged
    • Open items (if any)
    • Verdict: "Your plan is bulletproof" or "These areas still need work: ..."

Rules

  • Ask ONE question at a time — don't overwhelm
  • Don't give answers or suggestions — only ask questions
  • Don't implement anything — this is a thinking exercise
  • Be tough but not adversarial — the goal is to help, not to discourage
  • Cover ALL categories before concluding
  • If the user says "I don't know", that's an open item — note it and move on

Read the full file on GitHub · 49 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 · 49 lines · 50 tokens per session scan A f5a3bfbabd29

Subscribe to this mod's changes

grill-me is a skill published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 596 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 2026-08-31.