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 OutlineDriven/odin-gemini-cli-extension --skill grill-megit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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/outlinedriven/odin-gemini-cli-extension/grill-me)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/grill-me"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/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/outlinedriven/odin-gemini-cli-extension/grill-me"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/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 | $0.00083 | $0.01972 |
| Opus 5 | $0.00042 | $0.00986 |
| Sonnet 5 | $0.00017 | $0.00394 |
| Haiku 4.5 | $0.00008 | $0.00197 |
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.
This is a copy
100% identical to grill-me — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial interview. Walk every branch of the design tree; resolve dependencies one decision at a time; recommend an answer per question.
Modality disambiguation [LOAD-BEARING]
Three adjacent skills — pick the right one before invoking.
| Skill | Shape | Anchor | Output | Use when |
|---|---|---|---|---|
| clarifying-question protocol | VS-shaped — sample N intent hypotheses, rank, challenge each, then batch clarifying questions | None — pre-planning ambiguity | Survivor set + clarified scope | User intent is itself unclear |
| this skill | Linear adversarial interview, recommendation per question | None — design under test is the only anchor | Shared understanding, decision tree resolved | User has a plan/design and wants it stress-tested |
| domain-model grilling | Adversarial interview gated on documented domain language | CONTEXT.md + docs/adr/ |
Updated CONTEXT.md and/or new ADR |
Project has documented domain language to honour |
Rule of thumb: intent unclear → clarifying-question protocol. Plan exists, no domain rubric → this skill. Plan exists, domain rubric required → domain-model grilling.
Process
1. Anchor on the design under test
Confirm what the plan is in one sentence. If the user's pitch is too thin to interrogate, pivot to a clarifying-question protocol instead.
2. Walk the decision tree
For every fork in the design — scope, boundary, ordering, error surface, contract, naming, public-API shape, irreversibility — ask one question. Order by dependency: parents before children.
For each question:
- State the question precisely (one fact at a time).
- Recommend an answer with a one-sentence rationale.
- Wait for the user; never proceed on assumed answers.
3. Explore the codebase before asking when possible
If a question can be resolved by reading the code, read it instead of asking.
- Discovery:
fd -e <ext> <path>. - Structural search:
ast-grep run -p '<pattern>' -l <lang> -C 3. - Lexical search:
git --no-pager grep -n -C 3 '<pattern>'. - Targeted read:
bat -P -p -n -r START:END <path>. - Dispatch an Explore agent when the question spans >5 files or >2 directories.
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 · 145 lines · 83 tokens per session scan A f9dd03f91837
grill-me is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,972 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to grill-me, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…
grill-ai-mastery
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.