grill-me

grill-me is a skill for Claude Code from saitarrun/Devforge-ai. It costs 62 tokens per session (572 once invoked), scanned A, original, Apache-2.0.

A structured interview for testing a plan or design by examining its assumptions and decisions one question at a time.

In plain words
What is it for?
Use it to stress-test a product plan, technical design, or decision tree and reach a shared understanding of what should be built.
Why use it?
It exposes missing details, weak assumptions, and unresolved choices before implementation begins.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the devforge-ai plugin — 48 skills, 17 commands, 13 agents 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 skills/saitarrun/devforge-ai/grill-me
Any agent
npx skills add saitarrun/Devforge-ai --skill grill-me
Clone the repo
git clone --depth 1 https://github.com/saitarrun/Devforge-ai

Made for: Claude Code.

Or install devforge-ai, the plugin that ships this one along with the rest of its 48 skills, 17 commands, 13 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.

agentmods badge for grill-me

README.md
[![agentmods](https://agentmods.dev/badge/skills/saitarrun/devforge-ai/grill-me.svg)](https://agentmods.dev/skills/saitarrun/devforge-ai/grill-me)
Your own site
<a href="https://agentmods.dev/skills/saitarrun/devforge-ai/grill-me"><img src="https://agentmods.dev/badge/skills/saitarrun/devforge-ai/grill-me.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 572 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 $0.00062 $0.00572
Opus 5 $0.00031 $0.00286
Sonnet 5 $0.00012 $0.00114
Haiku 4.5 $0.00006 $0.00057

Measured 5d ago against content hash 2540d084eb95, 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 5d 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.

skills/grill-me/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Grill Me

Relentless design/plan review via structured interview. Walk down each branch of the decision tree, resolving dependencies between decisions one-by-one. Reach shared understanding by testing assumptions and exposing gaps.

Process

  1. Parse the plan/design — Identify key decisions, dependencies, assumptions
  2. Ask one question at a time — Deep on one branch; await answer before moving
  3. Explore codebase first — If a question is answerable by code inspection, do that instead of asking
  4. Provide recommended answer — For each question, suggest what you think is the right call (so user can react faster)
  5. Resolve branch completely — Don't jump to another decision until this one is fully understood
  6. Walk dependency tree — Only move to dependent decisions once blockers are cleared
  7. Reach shared understanding — Stop when both agree on the plan or user signals done

Question Structure

For each question:

**Q: [Question]**

My take: [Your recommended answer + reasoning]

What do you think?

When to Explore Code Instead

If user hasn't answered a question yet:

  • Design decision that's already implemented? Read the code.
  • Architecture pattern already in repo? Grep for examples.
  • Library choice already wired? Check package.json / imports.

This avoids asking about settled questions.

Decision Tree Example

Plan: Add user authentication

├─ Auth mechanism? (OAuth vs. session vs. JWT)
│  └─ Once decided → ask: which provider?
│     └─ Once decided → ask: token expiry strategy?
│        └─ Once decided → ask: refresh token rotation?
│
├─ DB schema for sessions/tokens?
│  └─ Once decided → ask: cleanup/revocation strategy?
│
├─ Rate limiting & brute force?
│  └─ Once decided → ask: lockout duration vs. progressive delay?

Only ask dependent questions after parent is resolved.

Stopping

User says: "stop grill", "that's enough", "I'm confident now"
You decide: "We've resolved the full decision tree and reached agreement."

Read the full file on GitHub · 70 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. 5d ago First seen · 70 lines · 62 tokens per session scan A 2540d084eb95

Subscribe to this mod's changes

grill-me is a skill published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 22d ago), licensed Apache-2.0. It adds 62 tokens to every session and 572 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.

Related

Other skills, from other repositories

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

moss-comments

Comment annotation and sidecar rules for Moss notes. Use when adding, replying to, resolving, preserving, or editing comments and comments.json.

brsbl/moss-skills · 32 tokens

icon-composer-app-icon-workflow

Design, preview, validate, and integrate Apple app icons with Icon Composer. Use when a task mentions Icon Composer, .icon documents, Liquid Glass app icons, ictool preview exports, app icon design for iOS, iPadOS, macOS, or watchOS, or guided Icon Composer GUI work through Computer Use.

gaelic-ghost/socket · 73 tokens

economics

Runtime subject skill payload for economics subject activation.

jxpeng98/qiongli · 12 tokens

rfc-impl-generator

Generate RFC and IMPL documents from a user-provided feature/fix description. Use when the user says something like "I want to add a feature with codex", "Implement this", "Write an RFC for...", or provides a short idea that needs to be formalized into the ai-driven/rfc + ai-driven/impl pipeline.

SepineTam/mcp-for-stata · 74 tokens

codexkit-repository-maintenance

Use when maintaining or improving the GameStudio-CodexKIT source repository, including CI, governance, catalog, generators, adapters, packaging, documentation, versioning, or release readiness.

hoatv2211/GameStudio-CodexKIT · 45 tokens