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 bendrucker/claude --skill grillinggit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/grilling)<a href="https://agentmods.dev/skills/bendrucker/claude/grilling"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/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/bendrucker/claude/grilling"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/grilling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 22 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Agent Snooping · line 22 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 58 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00058 | $0.00847 |
| Opus 5.5 | $0.00023 | $0.00339 |
| Sonnet 5.5 | $0.00012 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00085 |
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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grilling
Interview me about $ARGUMENTS until we reach a shared understanding. Do not act on it until I confirm we have.
Map the subject as a design tree: every decision branches into the decisions that hang off it. The frontier is every decision whose prerequisites are already settled, so its questions can be asked now without guessing at answers you have not heard. Work the frontier in rounds.
The decisions are mine. The facts are yours.
Question Shape
Every round's questions follow my standing AskUserQuestion rules:
!grep '^- ' ~/.claude/skills/ask/SKILL.md 2>/dev/null || echo '- **Fallback: no rule bullets found in ~/.claude/skills/ask/SKILL.md.** One question per open decision, a recommended option on every question, and split the batch when a follow-up depends on an earlier answer.'
Rounds
Ask the whole frontier in one round. AskUserQuestion caps a call at four questions, so when the frontier is wider, ask the four whose answers settle the most branches below them and name the deferred ones in prose. A question whose answer depends on another question open in this round belongs to a later round.
Say what the round is deciding before you call the tool. The widget renders the question and its options and nothing else, so the reasoning that led to this round has nowhere else to go.
Never ask whether to proceed. Permission to continue is not a decision.
Each round reshapes the tree. Settled decisions push the frontier outward and unblock what depended on them. Recompute it before asking again.
Finding Facts
Finding facts is your job. Never ask me for anything the repo, the filesystem, or a CLI can answer. Dispatch an analyst subagent on haiku or sonnet for each lookup and name what you sent it after.
Do not block on it. A running lookup is an unsettled prerequisite, so only the questions downstream of it wait. Ask the rest of the frontier now.
Options
Three options per question is the target and four is the ceiling. Across 2,398 questions asked this way, four-option questions came back overridden 43% of the time against 18% at two options, and a fifth option errors the call before I ever see it. A decision that needs five positions is two decisions.
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.
- 1mo ago First seen · 65 lines · 58 tokens per session scan A 47a179b1f635
grilling is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 847 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
pr-review
Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.
create-site
Creates a new Power Pages code site (SPA) from a curated template or from scratch using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, template selection or scaffolding, component planning, design, implementation, validation, and…
ensure-pipelines-host
Ensures the tenant has a usable Power Platform Pipelines host environment before any pipeline operation runs. Detects host state via the same resolution order as the Power Apps UI (org-db setting → BAP env metadata → default-custom-host setting); if any existing host (Platform or Custom) is found, uses it. If no host…