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 agentmods add skills/aethrox/doctrine/grillingnpx skills add aethrox/doctrine --skill grillinggit clone --depth 1 https://github.com/aethrox/doctrineWrote 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/aethrox/doctrine/grilling)<a href="https://agentmods.dev/skills/aethrox/doctrine/grilling"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/grilling.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00934 |
| Opus 5 | $0.00032 | $0.00467 |
| Sonnet 5 | $0.00013 | $0.00187 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
grilling 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 4d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grilling
An interview isn't a checklist of questions read out in order; it's closing a specific gap between what's already known and what's needed before acting. This skill's defining constraint, from BABOK's elicitation discipline: every question earns its place by targeting that gap, and nothing gathered is treated as settled until it's played back and confirmed. This is a business-analysis technique for the same reason it applies here: an unconfirmed answer is often not the answer that was meant.
Phase 1: Map the gap before asking anything
Before the first question, identify what's already known (from the conversation, the codebase, prior decisions) versus what's genuinely missing. A question that's already answerable from context doesn't belong in the interview, asking it anyway wastes the user's attention on ground already covered, and signals the interviewer wasn't listening.
Structure the missing pieces as a decision tree: each open decision, and which other open decisions it depends on. A decision with no unresolved dependency is on the frontier: answerable right now, without guessing at something not yet heard.
Phase 2: Elicit in rounds
Ask the whole frontier in one round, not one question at a time, batching respects the user's time and lets them see how the questions relate to each other. For each question:
- State it precisely enough that a specific answer, not a restatement of the question, is the expected response.
- Offer a recommended answer where one exists: a default the user can accept, correct, or override, rather than a blank slate they have to fill from nothing.
- Write questions and their surrounding prose without em dashes: use a comma, colon, period, or a reworded sentence instead.
Wait for the round's answers before computing the next round. Each answer can unblock questions that depended on it; recompute the frontier fresh each round rather than pre-planning every round up front, since an early answer can make a later planned question moot or reveal a new one.
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.
- 4d ago First seen · 48 lines · 63 tokens per session scan A 309fe62e6af8
grilling is a skill published in the GitHub repository aethrox/doctrine (18 stars, last pushed 23d ago), licensed MIT. It adds 63 tokens to every session and 934 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
planning-and-task-breakdown
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.