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 seaworld008/Commonly-used-high-value-skills --skill grill-megit clone --depth 1 https://github.com/seaworld008/Commonly-used-high-value-skillsWrote 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/seaworld008/commonly-used-high-value-skills/grill-me)<a href="https://agentmods.dev/skills/seaworld008/commonly-used-high-value-skills/grill-me"><img src="https://agentmods.dev/badge/skills/seaworld008/commonly-used-high-value-skills/grill-me/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/seaworld008/commonly-used-high-value-skills/grill-me"><img src="https://agentmods.dev/badge/skills/seaworld008/commonly-used-high-value-skills/grill-me.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 | $0.02051 |
| Opus 5.5 | $0.00014 | $0.00820 |
| Sonnet 5.5 | $0.00007 | $0.00410 |
| Haiku 4.5 | $0.00004 | $0.00205 |
Grade A, and why
grill-me 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 16d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill Me:方案追问与决策压力测试
把模糊的方案拆成有依赖关系的决策树,持续追问最有价值的未知项,直到双方对目标、约束、取舍和验收标准形成可核对的理解。 严谨针对方案,不针对人;指出矛盾和证据缺口,不用羞辱、争辩或问题数量来体现“强度”。
触发条件
用户明确说“grill me”“拷问一下这个方案”“挑战我的假设”“带我把需求问清楚”,或要求交互式设计审查时使用。 输入可以是 PRD、架构草案、迁移计划、产品想法、上线决策或一段尚未成型的描述。 仅要求安装、收录、审计或介绍这个技能,不代表用户要开始接受追问。 普通事实查询、已有明确验收标准的执行任务、紧急止损,不自动切换成访谈。
先建立决策树
先读取用户给出的方案及可用的项目证据,提取已确定的事实和决策。
用用户已有答案填树,不重新问预算、目标、技术栈等已明确的信息。
给每个会改变实现或验收的决策一个稳定编号,记录其前置条件和状态。
推荐状态:settled、open、needs-evidence、deferred、out-of-scope。
事实和偏好分开:代码是否支持回滚是事实,能接受多长回滚时间是决策。
D1 目标:在报名高峰保持可用 settled
├─ D2 可接受的数据损失和恢复时间 open
│ └─ D4 迁移、切换与回滚策略 blocked by D2
├─ D3 峰值流量及压测证据 needs-evidence
│ └─ D5 容量与扩容阈值 blocked by D3
└─ D6 本次是否包含跨地域容灾 open
树只覆盖本次决策范围,不无限扩展成整个组织的战略审查。 优先检查不可逆选择、高风险假设、失败代价和验收缺口,再处理可逆的小偏好。
按依赖关系组织每一轮
当前可问集合(frontier)是前置条件已经解决、现在回答不会依赖猜测的所有决策。 同一轮可以包含互相独立的问题;依赖本轮其他答案的问题放到下一轮。 每个问题提供建议答案和简短理由,但明确这是建议,不代替用户做价值判断。 用户要求一次只问一个时,按影响与不确定性排序,每轮取最重要的一项。 可问集合很大时按主题分批,并列出尚未讨论的分支,避免把长问卷直接倾倒给用户。
Q1 — 数据损失:切换失败时,是否允许丢失已确认成功的报名记录?
建议:不允许。将“已确认成功”定义为持久化提交成功,并纳入切换验收。
Q2 — 交付范围:这次是否必须具备跨地域容灾?
建议:先把同地域切换与回滚做实;跨地域作为单独里程碑,除非合同明确要求。
提问后等待本轮答案;不要替用户编造回答,也不要提前把下游设计当成已确定。 把答案更新到树中,说明哪些新问题因此解锁,再继续下一轮。 答案与此前决策冲突时,指出具体冲突和影响,询问应修订哪个决策。 答案不完整时只补问影响结论的部分,不重发整轮问题。
自己查事实,让用户做决定
能从仓库、配置、日志、文档或已连接工具查到的事实,先自行核对。
查不到时说明缺少的证据和它影响的决策,不把猜测包装成环境事实。
只有当前宿主实际提供子代理能力时才委派独立的只读调查;没有该能力就直接调查。
调查内容独立且工具允许时可以并行;否则顺序执行,不声称存在未启动的后台调查。
与待查事实无依赖的其他问题可以继续,相关分支保持 needs-evidence。
访问私人数据、运行命令、写入系统仍受用户授权和宿主权限约束。
用反例检验方案
对每个关键选择至少检查一个可能推翻它的条件,而不是机械地套用所有问题。
| 维度 | 有价值的追问 | 要得到的产物 |
|---|---|---|
| 目标 | 什么结果发生后,用户会认为这次投入值得? | 可观察的成功标准 |
| 约束 | 哪个约束不可突破,哪个只是当前偏好? | 硬约束与可协商项 |
| 证据 | 支撑这个容量、成本或收益判断的资料是什么? | 来源或待验证假设 |
| 替代方案 | 不做、延后、缩小范围会怎样? | 被放弃选项及理由 |
| 失败 | 最可能在哪一步失败,怎样发现并退出? | 失败信号与恢复条件 |
| 验收 | 谁在什么环境下,用什么数据判定完成? | 可重复的验收方式 |
数字建议必须注明依据或假设;不要把示例中的阈值变成用户系统的真实 SLO。 业务决定、风险接受和范围承诺归用户;可检索事实和技术推导由执行者提供证据。
收敛与交付
可问集合为空不等于所有问题都“已解决”:检查是否仍有未知前置条件、循环依赖或刻意跳过的分支。 循环依赖先找可逆的临时假设或最小实验,把“待验证”保留在输出中。 用户要求停止、缩小范围或先给结论时,及时收束,不坚持无限追问。 最终输出包括:方案目标、已确定决策、关键取舍、未解决项、验收标准和建议下一步。 每个未解决项写清影响、需要的证据及负责人(仅在已知时),不虚构完成日期。 只在当前授权覆盖实施且重大阻塞项已解决时进入执行;访谈本身不是部署、购买或删除的授权。 已有明确授权不必为每一个实现细节再设审批流程。
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.
- 16d ago First seen · 125 lines · 36 tokens per session scan A d9a98c3bc6dd
grill-me is a skill published in the GitHub repository seaworld008/Commonly-used-high-value-skills (73 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 2,051 once invoked, about $0.0001 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 2026-10-01.
Other skills, from other repositories
multi-perspective-meeting
Turn a single Agent into a full multi-perspective meeting. The Agent auto-generates one role-played participant per perspective, runs a structured debate with cross-examination, converges to a conclusion, and outputs an HTML meeting-minutes file. Trigger on any research / analysis / discussion / decision request.
omh-agent-evaluation
This is a Hermes-native agent-evaluation workflow skill.
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.
omh-morning-brief
This is a Hermes-native morning-brief workflow skill.
omh-research-department
This is a Hermes-native research-department workflow skill.
omh-websearch-setup
This is a Hermes-native websearch-setup workflow skill.