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 murray17/rovai-ai --skill grill-duogit clone --depth 1 https://github.com/murray17/rovai-aiWrote 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/murray17/rovai-ai/grill-duo)<a href="https://agentmods.dev/skills/murray17/rovai-ai/grill-duo"><img src="https://agentmods.dev/badge/skills/murray17/rovai-ai/grill-duo/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/murray17/rovai-ai/grill-duo"><img src="https://agentmods.dev/badge/skills/murray17/rovai-ai/grill-duo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.00953 |
| Opus 5 | $0.00051 | $0.00477 |
| Sonnet 5 | $0.00021 | $0.00191 |
| Haiku 4.5 | $0.00010 | $0.00095 |
Grade A, and why
grill-duo 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 11d 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.
What it actually says
双人追问
邀请者负责持续追问，一位固定搭档负责独立复核。能查明的事实由成员自行查找，真正需要取舍的决定交给用户。
角色与轮次关联
- 用户启动会话或回答当前开放轮次：作为邀请者继续。
- 当前 AgentRun 由普通双人追问复核请求直接触发：作为固定搭档，只处理当前请求。
- 当前输入是固定搭档对本轮有效邀请的直接回复：作为邀请者继续。
使用 Runtime 提供的可信发送者、当前触发消息和直接回复关系判断角色。邀请者只接受当前固定搭档对本轮有效邀请的直接回复；旧轮、失效或迟到建议只作补充，不能推进、回退或重开会话。
基本流程
- 选择合格的固定搭档，每轮整理 1–4 个前提已确认、彼此不依赖的问题。
- 把本轮问题一次发给搭档，不附带自己的推荐。
- 搭档用一条消息逐题返回建议、理由和风险。
- 邀请者结合双方判断，一次向用户提出全部开放问题并给出推荐。
- 用户回答后继续当前开放轮次；当前轮全部关闭后才整理下一轮。
- 没有重要问题后，请用户确认共同理解；确认前不开始实施。
依赖本轮其它答案的问题留到下一轮。能从代码、权威文档、工具、当前输入或 Camp 公共历史查明的事实，不问用户。
固定搭档
固定搭档必须不是自己、仍在当前 Camp、能够接收请求。使用可信 Agent ID 寻址，不根据显示名或正文猜测。优先选择最匹配的成员，整场保持固定；只有用户要求、搭档离场或不可用，或者问题进入其无法有效判断的领域时才更换，并说明原因。
没有合格搭档时，明确降级为单人追问并继续相同轮次，不虚构第二个观点。
开放轮次
一轮在所有问题被明确回答、取消或失效前保持开放，使用稳定编号 Q1–Q4。
- 未回答问题保留原编号、原问题和已有搭档建议；内容未变时不重复复核。
- 开放轮次期间不混入新问题。
- 用户改变某题的问题、选项或约束时保留编号，只重新复核该题；此后只采用搭档对更新邀请的直接回复。
- 用户只回答部分问题时，确认已关闭项并继续列出仍开放的原编号和已有建议。
消息方式
- 邀请者请求搭档：
rovai send --to <搭档 Agent ID> --body <本轮问题> - 搭档返回建议：
rovai send --to <邀请者 Agent ID> --body <本轮建议> - 邀请者询问用户或请求最终确认：
rovai send --to-user --body <正文>
使用可信 Agent ID。消息发送成功后结束当前响应；失败时按 CLI 返回指示处理，不盲目重发。
本轮内容
复核请求列出用户目标、已确认内容，以及每个问题的主要选项和重要约束。
搭档不得继续委派或增加问题，按原编号逐题给出建议、最主要理由和风险，不替用户决定或开始实施。
邀请者一次呈现全部开放问题，逐题说明主要取舍、自己的推荐和搭档看法；存在分歧时准确说明，并请用户按原编号回答。
完成
没有重要问题后，总结目标、已确认决定、关键约束和主要风险，并请求用户确认共同理解。用户确认后结束会话。
What ships with it
3 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.
- 11d ago First seen · 63 lines · 103 tokens per session scan A 828295fb59d0
grill-duo is a skill published in the GitHub repository murray17/rovai-ai (64 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 953 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
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
Read-only review
Review the selected implementation and report correctness, security, and maintainability findings. Do not modify workspace files.
debug-test-failure
Systematically diagnose a failing test instead of guessing at fixes.
write-runbook
Turn an incident response into a reusable runbook the next on-call can follow.
factory-render-verify
Render-and-measure receipts for any HTML page your factory builds — the render half of the design quality gate. Engineer runs it to screenshot every screen size and MEASURE what a source read or a single screenshot only guesses at: horizontal overflow, computed type sizes, tap-target sizes, safe-area presence, mono…
api-design-review
Review a new or changed API surface against the contract concerns that bite later.