grill-me

grill-me is a command for coding agents from refo/claude-dev-helpers. It costs 0 tokens per session (347 once invoked), scanned A, original, MIT.

A planning interview that asks one question at a time about a proposed design or implementation plan until its unclear parts and decisions are resolved.

In plain words
What is it for?
Use it to review product requirements, design documents, code comments, or an idea and turn them into a shared, clarified plan.
Why use it?
It exposes missing information, conflicting requirements, and weak assumptions before coding begins.

Command

Part of the dev-helpers plugin — 13 commands, 1 hook shipped together

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 commands/refo/claude-dev-helpers/grill-me
Clone the repo
git clone --depth 1 https://github.com/refo/claude-dev-helpers

Or install dev-helpers, the plugin that ships this one along with the rest of its 13 commands, 1 hook.

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/commands/refo/claude-dev-helpers/grill-me.svg)](https://agentmods.dev/commands/refo/claude-dev-helpers/grill-me)
Your own site
<a href="https://agentmods.dev/commands/refo/claude-dev-helpers/grill-me"><img src="https://agentmods.dev/badge/commands/refo/claude-dev-helpers/grill-me.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 347 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 $0.00000 $0.00347
Opus 5 $0.00000 $0.00173
Sonnet 5 $0.00000 $0.00069
Haiku 4.5 $0.00000 $0.00035

Measured 4d ago against content hash 9516aafd2a11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

plugins/dev-helpers/commands/grill-me.md · 47 lines

What it actually says

Grill Me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.

Workflow

1. Prepare

Read any existing documentation (PRDs, design docs, code comments) that define the plan or design. If nothing exists, ask the user to describe it.

2. Ask relentlessly

Your goal: identify and resolve uncertainties, ambiguities, or weak assumptions. Ask one question at a time. After the user answers, ask the next question — don't ask multiple questions in sequence.

When questions can be answered by exploring the codebase, do so. Otherwise, rely on the user.

Recommended structure for each question:

[brief context about why this matters]

[your question]

[your recommended answer, or "I don't have enough context to recommend"]

3. Refine

As the user clarifies, refine your understanding. When you identify a conflict or ambiguity in the plan:

  1. Call it out explicitly: "I'm hearing X from you here, but Y from you earlier — which is correct?"
  2. Record the resolution: add a note that this was clarified

4. Finish

When you've resolved enough of the decision tree that implementing the plan is now unambiguous, write a summary document. Ask the user: "Should I write this up as a PRD, a plan, a design doc, or something else?"

Then do it.

When to use

Use this skill when:

  • User asks to be "grilled" on a plan or design
  • User mentions "stress-test" or "poke holes"
  • You're about to build something and want to ensure shared understanding
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. 4d ago First seen · 47 lines · 0 tokens per session scan A 9516aafd2a11

Subscribe to this mod's changes

grill-me is a command published in the GitHub repository refo/claude-dev-helpers (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 347 tokens. 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.