grill-me

grill-me is a skill for Claude Code from seaworld008/Commonly-used-high-value-skills. It costs 36 tokens per session (2,051 once invoked), scanned A, original, MIT.

A guided questioning tool for stress-testing a plan, design, or decision. It maps assumptions, trade-offs, unanswered requirements, and dependencies instead of judging the person.

In plain words
What is it for?
Use it to examine product plans, architecture proposals, migration plans, or launch decisions, and to work through the most important open questions.
Why use it?
It exposes risky assumptions and missing evidence before implementation or commitment. It also prevents already-settled facts from being asked again.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to examine product plans, architecture proposals, migration plans, or launch decisions, and to work through the most important open questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/seaworld008/commonly-used-high-value-skills/grill-me
Install

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.

Any agent
npx skills add seaworld008/Commonly-used-high-value-skills --skill grill-me
Clone the repo
git clone --depth 1 https://github.com/seaworld008/Commonly-used-high-value-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for grill-me

README.md
[![agentmods](https://agentmods.dev/badge/skills/seaworld008/commonly-used-high-value-skills/grill-me/github.svg)](https://agentmods.dev/skills/seaworld008/commonly-used-high-value-skills/grill-me)
Your own site
<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.

agentmods 80×15 button for grill-me

Your own site · 80×15
<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>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,051 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 16d ago against content hash d9a98c3bc6dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

openclaw-skills/grill-me/SKILL.md · 125 lines

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。

Read the full file on GitHub · 125 lines

Files

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.

Changes

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.

  1. 16d ago First seen · 125 lines · 36 tokens per session scan A d9a98c3bc6dd

Subscribe to this mod's changes

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.