grill

A one-question-at-a-time review of a plan, specification, or topic designed to find gaps, contradictions, and dependencies before implementation. It can record the discussion and hand the refined result to planning.

In plain words
What is it for?
Use it to challenge a design or plan, examine risks and dependencies, refine the proposal, and prepare it for implementation planning.
Why use it?
It exposes weak assumptions and unanswered decisions while changes are still inexpensive. The focused questioning helps turn an uncertain proposal into a more definite direction.

Command

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/data-wise/craft/grill
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/craft
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 649 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 $0.00024 $0.00649
Opus 5 $0.00012 $0.00324
Sonnet 5 $0.00005 $0.00130
Haiku 4.5 $0.00002 $0.00065

Measured yesterday against content hash 8bf1582b19e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grill 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 yesterday.

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.

commands/grill.md · 52 lines

What it actually says

/craft:grill — Interrogate Before Building

This command is a thin shim. The canonical behavior lives in the grill skill. This file preserves the explicit /craft:grill slash entry point and owns the argument surface.

Convergent counterpart to /craft:brainstorm: brainstorm is divergent (generates options); grill is convergent (interrogates a position to find gaps, contradictions, and unresolved dependencies before you implement).

When Invoked

  1. Load the canonical procedure: read ${CLAUDE_PLUGIN_ROOT:-.}/skills/workflow/grill/SKILL.md and follow it exactly — resolve target, codebase-first pre-answer sweep, select attack angles, the deliberate one-question-at-a-time grill loop (Recommended-first + per-option consequence), milestone checkpoints, durable GRILL-*.md capture via commands/utils/grill_ledger.py, and the one-directional handoff into /craft:plan.
  2. Do not reimplement here. Any change to grill behavior must be made in the skill, never duplicated into this shim.

The flags above (--bound, --no-capture, --yes/--non-interactive, --refine/--no-refine, --no-tests/--no-docs) are parsed here and passed through to the skill.

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. yesterday First seen · 52 lines · 24 tokens per session scan A 8bf1582b19e2

Subscribe to this mod's changes

grill is a command published in the GitHub repository Data-Wise/craft (4 stars, last pushed 16d ago), licensed MIT. It adds 24 tokens to every session and 649 once invoked, about $0.0001 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.