grill-me

grill-me is a skill for Claude Code, Codex from feiskyer/codex-settings. It costs 71 tokens per session (1,996 once invoked), scanned A, a copy of grill-me, MIT.

A guided questioning procedure for challenging a plan or design one decision at a time. It also records agreed terms and architectural decisions in context files and architecture decision records, documents that explain important design choices.

In plain words
What is it for?
Use it only when explicitly asking to be questioned or challenged about a proposal. It checks existing context and decision records, asks one question at a time, and waits for confirmation before execution.
Why use it?
It exposes unclear assumptions and edge cases before implementation begins. It keeps the discussion aligned with the project’s existing terminology and records decisions for later reference.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/feiskyer/codex-settings/grill-me
Any agent
npx skills add feiskyer/codex-settings --skill grill-me
Clone the repo
git clone --depth 1 https://github.com/feiskyer/codex-settings

Made for: Claude Code, Codex.

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/feiskyer/codex-settings/grill-me.svg)](https://agentmods.dev/skills/feiskyer/codex-settings/grill-me)
Your own site
<a href="https://agentmods.dev/skills/feiskyer/codex-settings/grill-me"><img src="https://agentmods.dev/badge/skills/feiskyer/codex-settings/grill-me.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,996 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00071 $0.01996
Opus 5 $0.00036 $0.00998
Sonnet 5 $0.00014 $0.00399
Haiku 4.5 $0.00007 $0.00200

Measured 5d ago against content hash 526af77ba55b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 5d 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.

Origin

This is a copy

86% identical to grill-me — 4 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.

skills/grill-me/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

追问会话

启动步骤

触发后,先执行以下检查:

  1. 检查项目根目录是否已有 CONTEXT.mdCONTEXT-MAP.md,有则读取
  2. 检查 docs/adr/ 是否已有 ADR 记录,有则了解已有决策
  3. 然后开始追问

核心规则

针对方案的每一个方面进行不留死角的追问,直到我们达成共识。沿着设计决策树逐一走下去,逐条解决决策之间的依赖关系。每个问题给出你的推荐答案。

一次只问一个问题,等我回复后再继续下一个。一次抛出多个问题会让人无所适从。

如果某个事实可以通过探索代码库获得,就直接查找,不要问我。但决策权在我——每个决策都提给我,等我回答。

在我明确确认达成共识之前,不要开始执行方案。


领域建模(内置流程)

追问过程中,一旦有决策结晶,就立即建立和完善项目的领域模型——挑战术语、构造边界场景、在第一时间写下术语表和决策记录。

文件结构

大多数仓库只有单一上下文:

/
├── CONTEXT.md
├── docs/
│   └── adr/
│       ├── 0001-event-sourced-orders.md
│       └── 0002-postgres-for-write-model.md
└── src/

如果根目录存在 CONTEXT-MAP.md,则表示仓库有多个上下文,地图指向各自位置:

/
├── CONTEXT-MAP.md
├── docs/
│   └── adr/                          ← 系统级决策
├── src/
│   ├── ordering/
│   │   ├── CONTEXT.md
│   │   └── docs/adr/                 ← 上下文专属决策
│   └── billing/
│       ├── CONTEXT.md
│       └── docs/adr/

懒创建——只在有内容可写时才创建文件。如果 CONTEXT.md 不存在,在第一个术语确定时创建它。如果 docs/adr/ 不存在,在第一个 ADR 需要时创建它。

追问过程中的行为

对照术语表质疑

当用户使用的术语与 CONTEXT.md 中已有定义冲突时,立即指出:"你的术语表把'取消'定义为 X,但你现在似乎是指 Y——到底是哪个?"

磨尖模糊表达

当用户使用含糊或多义的词汇时,提出精确的规范术语:"你说的'账户'——是指 Customer 还是 User?这是两个不同概念。"

讨论具体场景

讨论领域关系时,用具体场景压力测试。构造探索边界条件的场景,迫使用户精确界定概念之间的边界。

与代码交叉验证

当用户陈述某物如何运作时,检查代码是否一致。如果发现矛盾,立即暴露:"你的代码取消的是整个 Order,但你刚说可以部分取消——哪个是对的?"

即时更新 CONTEXT.md

术语一旦敲定,立即更新 CONTEXT.md,不要攒着批量处理。格式参见下方「CONTEXT.md 格式」章节。

CONTEXT.md 必须完全不含实现细节。不要把它当规格文档、草稿本或实现决策仓库。它只是术语表。

审慎提供 ADR

仅当以下三条全部成立时才创建 ADR:

  1. 难以逆转 — 将来改变主意的代价可观
  2. 缺乏上下文则令人费解 — 未来读者会困惑"为什么这样做?"
  3. 确实是权衡的结果 — 存在真正的替代方案,且你基于具体理由选了其一

参考:CONTEXT.md 格式

结构

# {上下文名称}

{一两句话描述这个上下文是什么、为什么存在。}

## 语言

**订单(Order)**:
{一两句话定义该术语}
_避免使用_: Purchase, transaction

**发票(Invoice)**:
向客户发送的交付后付款请求。
_避免使用_: Bill, payment request

**客户(Customer)**:
下订单的个人或组织。
_避免使用_: Client, buyer, account

注:示例语言应跟随项目主语言。中文项目用中文术语,英文项目用英文术语。

规则

  • 有主张。 当多个词指代同一概念时,选最好的那个,其余列入 _避免使用_
  • 定义简洁。 最多两句话。定义它什么,而非它做什么。
  • 只收录项目上下文专属术语。 通用编程概念不属于这里。
  • 出现自然聚类时分组。 若所有术语属于同一领域,平铺即可。

Read the full file on GitHub · 198 lines

Files

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.

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. 5d ago First seen · 198 lines · 71 tokens per session scan A 526af77ba55b

Subscribe to this mod's changes

grill-me is a skill published in the GitHub repository feiskyer/codex-settings (237 stars, last pushed 22d ago), licensed MIT. It adds 71 tokens to every session and 1,996 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to grill-me, differing in 4 lines, and is treated as a copy.