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.
npx skills add Rijul1204/rashedul-agentic-engineering --skill grill-megit clone --depth 1 https://github.com/Rijul1204/rashedul-agentic-engineeringWrote 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.
[](https://agentmods.dev/skills/rijul1204/rashedul-agentic-engineering/grill-me)<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.
<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>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 | $0.00121 | $0.01696 |
| Opus 5 | $0.00060 | $0.00848 |
| Sonnet 5 | $0.00024 | $0.00339 |
| Haiku 4.5 | $0.00012 | $0.00170 |
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.
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.
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.
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.
- 9d ago First seen · 99 lines · 121 tokens per session scan A 4e60b334676c
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.
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…
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…
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.…
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…
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…
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.