grill-me

grill-me is a skill for Claude Code, Codex from Rijul1204/rashedul-agentic-engineering. It costs 121 tokens per session (1,696 once invoked), scanned A, original, MIT.

A structured interview process for examining a software plan or design before implementation. It asks focused questions about decisions, assumptions, dependencies, edge cases, and success criteria.

In plain words
What is it for?
Pressure-test a proposed feature, architecture, or delivery approach. It helps reach a decision-complete plan or identify the decisions that still block implementation.
Why use it?
It prevents work from starting with important choices left vague. It helps uncover problems such as partial failures, unclear ownership, or missing limits.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Pressure-test a proposed feature, architecture, or delivery approach. It helps reach a decision-complete plan or identify the decisions that still block implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rijul1204/rashedul-agentic-engineering/grill-me
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 Rijul1204/rashedul-agentic-engineering --skill grill-me
Clone the repo
git clone --depth 1 https://github.com/Rijul1204/rashedul-agentic-engineering

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.

agentmods badge for grill-me

README.md
[![agentmods](https://agentmods.dev/badge/skills/rijul1204/rashedul-agentic-engineering/grill-me/github.svg)](https://agentmods.dev/skills/rijul1204/rashedul-agentic-engineering/grill-me)
Your own site
<a href="https://agentmods.dev/skills/rijul1204/rashedul-agentic-engineering/grill-me"><img src="https://agentmods.dev/badge/skills/rijul1204/rashedul-agentic-engineering/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.

agentmods 80×15 button for grill-me

Your own site · 80×15
<a href="https://agentmods.dev/skills/rijul1204/rashedul-agentic-engineering/grill-me"><img src="https://agentmods.dev/badge/skills/rijul1204/rashedul-agentic-engineering/grill-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,696 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.01696
Opus 5 $0.00060 $0.00848
Sonnet 5 $0.00024 $0.00339
Haiku 4.5 $0.00012 $0.00170

Measured 9d ago against content hash 4e60b334676c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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 · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grill Me

Interview the user relentlessly about every aspect of a plan, design, or approach until shared understanding lands. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For every question, supply your recommended answer + the rationale + what changes if the opposite is chosen.

See README.md for the credit (Matt Pocock's original grill-me) and install / use instructions.

Philosophy: peer programmer, not executor

The default agent mode is execute the user's stated request. That's the wrong mode when the request itself is underspecified — and in real engineering, underspecification is the norm. grill-me flips the polarity: before you start, you act as a peer engineer who would push back on a colleague handing you the same brief.

Concretely:

  • Ask the hard questions first. Not "what colour should the button be?" — "what happens if the upstream service returns partial data?", "who decides when this feature is done?", "is this a real user need or a guess?"
  • Push for explicit, defensible answers. "We'll figure it out later" isn't an answer. Either pin it now or name it as a deferred decision with a revisit trigger.
  • Make the decision tree visible. Every decision branches. Drawing the tree (even in prose) surfaces dependencies the user was carrying silently.
  • Recommend, don't just ask. A peer engineer doesn't say "what should we do?" with no opinion. Lead with your recommendation, justify it, then ask whether they buy it.

When to invoke

Fire on:

  • User types /grill-me.
  • User says "grill me on this", "stress-test this plan", "interview me", "challenge my approach", "what am I missing?", "are there gaps?".
  • User just finished writing a plan / spec / design doc and asks for review before implementation starts.
  • You're about to start a non-trivial task and the brief feels underspecified — invoke proactively rather than starting work on guesses.

Do NOT fire on:

  • Trivial tasks with a concrete brief (one-line fix, a rename).
  • Implementation in progress — interrupting with grill questions mid-task is friction, not value. Front-load the grilling.

Read the full file on GitHub · 99 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 99 lines · 121 tokens per session scan A 4e60b334676c

Subscribe to this mod's changes

grill-me is a skill published in the GitHub repository Rijul1204/rashedul-agentic-engineering (2 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 1,696 once invoked, about $0.0006 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

ios-app-agentic-engineering

End-to-end agentic engineering for iPhone apps, from idea to a secure App Store release through 8 gated phases. Use when someone wants to build, plan, or ship an iPhone/iOS app — especially a non-programmer ("vibe coder") asking to create an app, pick a tech stack (SwiftUI, React Native, Flutter), choose a backend…

markus-smile/ios-app-agentic-engineering · 138 tokens

stakeholder-communication

Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…

rampstackco/claude-skills · 103 tokens

analytics-strategy

Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…

rampstackco/claude-skills · 126 tokens

content-strategy

Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align…

rampstackco/claude-skills · 120 tokens

incident-response

Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…

rampstackco/claude-skills · 117 tokens

agb-begriff-vorformuliert-305

Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.

Klotzkette/claude-fuer-deutsches-recht · 68 tokens