A planning interview that stress-tests a proposed direction by asking the human each unresolved question in dependency order. Each question includes a suggested answer, and later questions wait for earlier decisions.

Use it to clarify a plan, design, or project direction until its important decisions are settled.

It exposes missing decisions before work begins and avoids asking questions whose answers depend on choices that have not been made.

grill — Skill for Claude Code by haowjy/creative-writing-skills

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 haowjy/creative-writing-skills --skill grill

Clone the repo

git clone --depth 1 https://github.com/haowjy/creative-writing-skills

Made for: Claude Code.

Or install creative-writing-skills, the plugin that ships this one along with the rest of its 28 skills, 5 agents.

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/haowjy/creative-writing-skills/grill/github.svg)](https://agentmods.dev/skills/haowjy/creative-writing-skills/grill)

Your own site

<a href="https://agentmods.dev/skills/haowjy/creative-writing-skills/grill"><img src="https://agentmods.dev/badge/skills/haowjy/creative-writing-skills/grill/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/haowjy/creative-writing-skills/grill"><img src="https://agentmods.dev/badge/skills/haowjy/creative-writing-skills/grill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 210 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	$0.00038	$0.00210
Opus 5.5	$0.00015	$0.00084
Sonnet 5.5	$0.00008	$0.00042
Haiku 4.5	$0.00004	$0.00021

Measured 10d ago against content hash 45f159a3e58a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 10d 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.

plugin/claude/skills/grill/SKILL.md · 25 lines

What it actually says

Grill

Load /creative-writing-skills:intent-modeling if it isn't already loaded.

Interview the human relentlessly about the plan or direction until you reach a shared understanding. Map it as a decision tree: each decision branches into the decisions that hang off it.

Work in rounds. Each round, ask every question whose prerequisites are already settled, numbered, each with your recommended answer, worded so "yes" accepts the recommendation. A question that depends on another one still open waits for a later round. After the answers, recompute what is now askable and run the next round. Finish when no question is left open.

Facts are yours to find: read artifacts and source material instead of asking. Decisions are the human's.

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.

10d ago First seen · 25 lines · 38 tokens per session scan A 45f159a3e58a

Subscribe to this mod's changes

grill is a skill published in the GitHub repository haowjy/creative-writing-skills (567 stars, last pushed 10d ago), licensed Apache-2.0. It adds 38 tokens to every session and 210 once invoked, about $0.0002 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 2026-10-28.

Planning

grill next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
grillhaowjy/creative-writing-skills	Skill	567	10d ago	Apache-2.0	A	38	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code