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-codex-plugin --skill grill-ai-masterygit clone --depth 1 https://github.com/OutlineDriven/odin-codex-pluginWrote 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-codex-plugin/grill-ai-mastery)<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/grill-ai-mastery"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/grill-ai-mastery.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 5.1 | $0.00104 | $0.01949 |
| Opus 5 | $0.00052 | $0.00975 |
| Sonnet 5 | $0.00021 | $0.00390 |
| Haiku 4.5 | $0.00010 | $0.00195 |
Grade A, and why
grill-ai-mastery 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- grill-ai-mastery — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Probe AI mastery by what the subject names, not by how much they generate. The premise from the chat that prompted this skill: token usage and LOC are noise; concrete tip vocabulary (URL-as-entity-ref, loop closure, observability) is signal.
Mode disambiguation
| Skill | Anchor | Posture |
|---|---|---|
grill-ai-mastery |
AI-collab tip vocabulary tree (this file) | Hybrid: collaborative → adversarial |
grill-me |
Any plan/design under test | Linear adversarial, recommendation per question |
request-refactor-plan |
A refactor in particular | Adversarial interview specific to refactoring |
This skill is the AI-mastery anchor; grill-me is the domain-agnostic version. Pick by what's being assessed.
Phase 1 — Collaborative tip-sharing
Open by asking the subject to name a tip they actually use when collaborating with an LLM. Two-way: surface one of yours back as a counter-tip. The exchange is the assessment, not a quiz. Watch for:
- Concrete protocol names (URL-as-entity-ref, AGENTS.md, MCP resources, structured outputs) versus generic platitudes ("I write good prompts").
- Direction-of-travel signals — does the subject describe loops, observability, anchored references? Or do they describe vibes, screenshots, "the function we discussed"?
- Self-correction — when the subject reaches for a vague handle, do they catch themselves and produce a URL?
Stay collaborative as long as the depth matches the level the assessment is calibrated to.
Phase 2 — Adversarial probe (escalation)
Promote to adversarial questioning when any of these signals fire:
- Vague answers — "I just use it normally" / "good prompts" / "I check the output" with no protocol name attached.
- Token-usage / LOC framing — the explicit anti-pattern from the chat that prompted this skill. Surface the rejection: "those measure quantity, not capability. What do you actually do that someone less skilled does not?"
- Inability to name three protocols — when prompted directly, cannot produce three concrete tactics with a why for each.
- Unanchored entity references in the conversation itself — the subject says "the PR" / "that bug" without offering a URL.
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.
- 8d ago First seen · 121 lines · 104 tokens per session scan A 730baaf0b6e0
grill-ai-mastery is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (15 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 104 tokens to every session and 1,949 once invoked, about $0.0005 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
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…
create-interactive-slides
A tool for turning a talk, lesson, or product demonstration into an interactive HTML, CSS, and JavaScript slide deck with a storyboard, presenter notes, and rehearsal cues.
git-guardrails-claude-code
Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.
duet
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.
explore
Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Uses a staged 1/3/5 Explore-agent escalation protocol scaled to scope.…
deps-upgrade
Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings…