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 escoffier-labs/skillet --skill grillgit clone --depth 1 https://github.com/escoffier-labs/skilletWrote 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/escoffier-labs/skillet/grill)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/grill"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/grill/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/escoffier-labs/skillet/grill"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/grill.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 | $0.00110 | $0.01425 |
| Opus 5 | $0.00055 | $0.00713 |
| Sonnet 5 | $0.00022 | $0.00285 |
| Haiku 4.5 | $0.00011 | $0.00143 |
Grade A, and why
grill 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 10d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grill
On Hacker News and Lobsters the top comment is usually someone who has done the exact thing you wrote about. Grilling is the pass that gets a post ready to be read by that person: every claim sourced or flagged, the voice de-hyped, the story real instead of impressive, and the obvious objections already answered. You are not writing for the upvote. You are writing for the skeptic who has been here before.
Core principle: a fabricated specific is the fastest way to lose the thread to the one reader who knows. Flag what you cannot verify; never dress a gap as confidence.
The pass (run in order)
-
Voice: kill the underdog. Strip the effort-proving "I did X, I did Y, I opened the chassis, I ran the cabling" cadence. The byline already says you did the work; arguing it reads as insecure. Tell the story and let the specifics carry it. Cut sentences that exist only for rhythm or motivation ("That is the job.", "future pain with confidence.").
-
Slop: strip the AI tells and empty hedges. Run
scripts/grill-scan.sh <file>for the mechanical hits (slop vocabulary, hedge phrases, em dashes, the rhythmic "That is X." tic), then read by eye for the rest. The scan is a floor, not the check. -
Facts: source every number, price, date, version, and third-party claim, or flag it. For anything you cannot verify against a primary source, leave a literal
[CONFIRM: what's needed]marker in the draft. Do not invent a plausible config value, log line, or figure to fill the gap. Look facts up yourself before asking the human; only escalate the ones that survive a real search. -
Right-number check. A fact can be genuinely real and still be the wrong fact for this post. Confirm the claim matches the specific setup, not just that the value exists somewhere (quoting the full-bundle list price when the project ran the base edition; citing a benchmark from different hardware). Verified-real is not verified-relevant.
-
Freshness check. Vendor pricing, policies, and "minimums" get reversed, and versions move. Date-check any claim about how a third party behaves and note when it was true, so a since-changed fact reads as history, not error.
What ships with it
4 files 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.
- 10d ago First seen · 66 lines · 110 tokens per session scan A 426277d6d29e
grill is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 9d ago), licensed MIT. It adds 110 tokens to every session and 1,425 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
assess-interview-candidate
A structured hiring-assessment workflow that turns a candidate's résumé and a job description into reviewable evidence, interview questions, and an offline HTML report for interviewers.
task-clarifier
Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task…
user-profile-keeper
Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes $user-profile-keeper to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. It can extract durable collaboration…
run-history-skill-builder
Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons…
run-history-skill-upgrader
Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed…
session-handoff-prompt
Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries…