A one-on-one questioning method for testing a plan, build, or decision. It asks one question at a time and suggests a strong answer to help reveal weak assumptions.

Pressure-testing plans, product ideas, builds, and important decisions before committing to them.

It helps separate real risks from hesitation before work begins. Unlike a group debate, it keeps the discussion focused on the user's goals.

grill-me — Skill for Claude Code and Codex by mshadmanrahman

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/claudecode-guide --skill grill-me

Clone the repo

git clone --depth 1 https://github.com/mshadmanrahman/claudecode-guide

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mshadmanrahman/claudecode-guide/grill-me/github.svg)](https://agentmods.dev/skills/mshadmanrahman/claudecode-guide/grill-me)

Your own site

<a href="https://agentmods.dev/skills/mshadmanrahman/claudecode-guide/grill-me"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claudecode-guide/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mshadmanrahman/claudecode-guide/grill-me"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claudecode-guide/grill-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,645 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.

Model	Per session	Once invoked
Fable 5.1	$0.00084	$0.01645
Opus 5.5	$0.00034	$0.00658
Sonnet 5.5	$0.00017	$0.00329
Haiku 4.5	$0.00008	$0.00164

Measured 6d ago against content hash ce517c7292df, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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.

public/skills/grill-me/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grill Me

A live interrogation. Not a council and not a verdict: a one-on-one that keeps asking the next question until the user's thinking holds up, before they commit to a plan, a build or a decision.

If the Crucible skill is installed, it convenes a council and returns a verdict. Grill Me stays in the room and asks the next question.

When to activate

"Grill me on..."
"Grill this idea"
"/grill-me"
"Am I thinking about this right?"
"Help me think through..."
"Before I build this..."
"Let's pressure-test this"
"I'm about to [plan / commit / ship / pitch] X"

Know who you are grilling

Before the first real question, find the user's goals. Check the project's CLAUDE.md or any notes they point you to. If nothing states them, ask once:

"Before we start: what's the bigger goal this should serve? One line for money or business, one line for your own growth."

Keep both answers in mind for the whole session. Never read them back word for word.

Common patterns to probe (watch for them, don't assume them):

Spreading thin across too many things, so everything gets shallow execution.
Self-doubt dressed as caution. Separate real risk from nerves.
Feature ideas before any signal. "Wouldn't it be cool if..." is not a case.
Scope creep mid-build. What was a fix becomes a refactor.
Avoidance dressed as thoroughness. Asking more questions instead of deciding.

How to run the dialogue

Step 1: identify the topic. If the user hasn't said what they want grilled, ask: "What are we grilling? Give me the topic in one sentence."

Step 2: pick the lens. Choose one primary lens from the list below based on the topic. Announce it so the user knows the frame you're using.

Step 3: one question per turn, with a recommended answer. Format every question like this:

Question: [the question]

My read: [your recommended answer based on what you know so far, in 1-2 sentences. The user can confirm, correct or expand.]

Never ask two questions in the same turn. Never offer analysis before you've asked enough questions to earn it.

Read the full file on GitHub · 154 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.

6d ago First seen · 154 lines · 84 tokens per session scan A ce517c7292df

Subscribe to this mod's changes

grill-me is a skill published in the GitHub repository mshadmanrahman/claudecode-guide (45 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 1,645 once invoked, about $0.0003 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 2026-10-31.

Claude Code Learning and teaching Planning ai-coding ai-tools anthropic claude developer-tools

grill-me next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
grill-memshadmanrahman/claudecode-guide	Skill	45	2d ago	MIT	A	84	Claude Code, Codex
career-path-plannertravisjneuman/.claude	Skill	107	yesterday	MIT	A	41	Claude Code, Codex
case-interview-practicetravisjneuman/.claude	Skill	107	yesterday	MIT	A	39	Claude Code, Codex
debate-practice-coachtravisjneuman/.claude	Skill	107	yesterday	MIT	A	45	Claude Code, Codex
onboarding-guide-creatortravisjneuman/.claude	Skill	107	yesterday	MIT	A	37	Claude Code, Codex
course-material-creatortravisjneuman/.claude	Skill	107	yesterday	MIT	A	40	Claude Code, Codex
learning-gap-analyzertravisjneuman/.claude	Skill	107	yesterday	MIT	A	36	Claude Code, Codex