Borrowing it
Nothing to install: this file belongs to christopher-buss/bedrock. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/christopher-buss/bedrock/main/.agents/skills/grilling/SKILL.mdgit clone --depth 1 https://github.com/christopher-buss/bedrockWrote 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/christopher-buss/bedrock/grilling)<a href="https://agentmods.dev/skills/christopher-buss/bedrock/grilling"><img src="https://agentmods.dev/badge/skills/christopher-buss/bedrock/grilling/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/christopher-buss/bedrock/grilling"><img src="https://agentmods.dev/badge/skills/christopher-buss/bedrock/grilling.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 | $0.00038 | $0.00561 |
| Opus 5.5 | $0.00015 | $0.00224 |
| Sonnet 5.5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
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 5d 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 grilling — 23 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.
What it actually says
Interview the user relentlessly until you reach a shared understanding. Map this as a design tree: every decision branches into the decisions that hang off it.
Work the tree in rounds. The frontier is every decision whose prerequisites are already settled: the questions you can ask now without guessing at answers you haven't heard yet. A round is the top three frontier questions, ranked by how many downstream decisions each unblocks; the rest of the frontier waits for a later round. Ask the round, then wait for the user's answers.
The user skims. A round is skimmable: recommendation before question, one line per part, plain numbered text.
Write every round, expansion, and summary in ASD-STE100 Simplified Technical English, and name things with the ubiquitous language from GLOSSARY.md (follow GLOSSARY-MAP.md to the right one if the repo has more than one).
Format a round like so:
Round . settled. open. waiting. Reply with only the numbers you disagree with. Silence accepts the recommendation.
-
<title, one line> -> Recommend: Question:
-
...
Header counts: settled = decisions answered so far; open = questions in this round; waiting = frontier questions held back.
Each round the user answers reshapes the tree: a number the user leaves unmentioned settles on the recommendation; settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a later round, not this one. When the user says "expand N", give the full reasoning for that one question, then wait.
Finding facts is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The decisions are the user's: put each to them and wait.
The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.
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.
- 5d ago Changed · +3 lines 6bda9e69d133
- 1mo ago First seen · 29 lines · 38 tokens per session scan A 10ff989e7498
grilling is a skill published in the GitHub repository christopher-buss/bedrock (19 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 561 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to grilling, differing in 23 lines, and is treated as a copy.
Other skills, from other repositories
x-demand-radar
A radar for spotting fast-rising topics, tools, and projects on X, the social network formerly known as Twitter.
null-axiom-twitter
A writing tool that creates Twitter/X posts and threads in the Null Axiom persona, with a style aimed at indie developers and data-focused investigators. It can also draft replies to Twitter/X posts and send drafts to Feishu for review on a schedule.
roblox-site-architect
Orchestrate an evidence-backed seven-stage Roblox site growth pipeline from opportunity assessment through keyword research, source collection, site planning, SEO QA, freshness, and growth. Use when work needs staged artifacts and explicit handoffs rather than a one-click site generator.
site-keyword-research
A website keyword-research workflow that studies what people search for, expands related terms, and analyses competition in search results.
roblox-homepage-ranking-auditor
Audit a Roblox or game-site homepage against the RB Auto Golden Homepage model. Use when Codex must inspect a live homepage or repository, identify the primary player job and main engine, score structural ranking potential across eight dimensions, detect empty query modules, weak information gain, root/child intent…
roblox-hit-evaluator
Evaluate a Roblox game's 30-day breakout potential from public evidence with auditable scores, missing-data bounds, frozen forecasts, and outcome reviews.