Borrowing it
Nothing to install: this file belongs to modelstudioai/OpenAgentPack. 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/modelstudioai/OpenAgentPack/main/.agents/skills/grilling/SKILL.mdgit clone --depth 1 https://github.com/modelstudioai/OpenAgentPackWrote 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/modelstudioai/openagentpack/grilling)<a href="https://agentmods.dev/skills/modelstudioai/openagentpack/grilling"><img src="https://agentmods.dev/badge/skills/modelstudioai/openagentpack/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/modelstudioai/openagentpack/grilling"><img src="https://agentmods.dev/badge/skills/modelstudioai/openagentpack/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 | $0.00036 | $0.00127 |
| Opus 5.5 | $0.00014 | $0.00051 |
| Sonnet 5.5 | $0.00007 | $0.00025 |
| Haiku 4.5 | $0.00004 | $0.00013 |
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.
This is a copy
100% identical to grilling — 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.
What it actually says
Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
Ask the questions one at a time, waiting for feedback on each question before continuing. Asking multiple questions at once is bewildering.
If a question can be answered by exploring the codebase, explore the codebase instead.
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 · 11 lines · 36 tokens per session scan A fe00af3e1815
grilling is a skill published in the GitHub repository modelstudioai/OpenAgentPack (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 127 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to grilling, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
clawbench-base
Run and diagnose ClawBench evaluations through ClawMind and ClawWeb. Use when the user wants to trigger /clawbench, inspect benchmark progress, locate run artifacts, or troubleshoot evaluation execution.
clawbench-report
A workflow that reads one ClawBench evaluation and writes a Markdown diagnostic report. The report can summarize scores, task outcomes, failures, evidence, and likely causes when the data is available.
test-driven-development
Use when adding any new behavior or fixing any bug. Red → Green → Refactor, enforced.
test-as-self
Deploy the current instar dist into a throwaway agent home and verify the deploy is healthy — clean evidence instead of post-hoc log forensics. Use BEFORE shipping a change that touches the deploy/lifeline/server path; AFTER landing such a change; or to reproduce a crash observed in the wild.
ocm-integrations
Use OCM workspace integrations exposed by the native mcp.servers.ocm MCP server. Trigger when a user asks to use connected workspace apps or external SaaS tools such as Google Workspace, GitHub, Jira, Linear, Slack, Notion, custom REST APIs, OpenAPI tools, or remote MCP servers through OCM.
aar-operations
Operate the Adaptive Agent Runtime through its public MCP tools. For tasks that need tool use or analysis, consider AAR MCP early when bounded stateful computation, brokered jobs, operations, contracts, or artifacts can materially help; software planning, development, testing, and troubleshooting belong to this class…