C31-grill

C31-grill is a skill for Claude Code, Codex from ChianW/C31. It costs 54 tokens per session (2,705 once invoked), scanned A, original, MIT.

A structured questioning process for plans and designs before substantial coding work begins. It asks one question at a time, clarifies unfamiliar terms and decisions, and records agreed definitions and choices in project documents.

In plain words
What is it for?
Use it to examine a feature plan, architecture decision, or other large task branch by branch. It can also build or update a project glossary and decision record as answers are confirmed.
Why use it?
It reduces misunderstandings about what a project should do and exposes unresolved dependencies before work starts. It is especially suited to tasks involving multiple files or significant time.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it to examine a feature plan, architecture decision, or other large task branch by branch. It can also build or update a project glossary and decision record as answers are confirmed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chianw/c31/c31-grill
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 ChianW/C31 --skill c31-grill
Clone the repo
git clone --depth 1 https://github.com/ChianW/C31

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 C31-grill

README.md
[![agentmods](https://agentmods.dev/badge/skills/chianw/c31/c31-grill.svg)](https://agentmods.dev/skills/chianw/c31/c31-grill)
Your own site
<a href="https://agentmods.dev/skills/chianw/c31/c31-grill"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-grill.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,705 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 $0.00054 $0.02705
Opus 5 $0.00027 $0.01352
Sonnet 5 $0.00011 $0.00541
Haiku 4.5 $0.00005 $0.00270

Measured 8d ago against content hash 85c230a0d1f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

C31-grill 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 8d 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.

skills/core/C31-grill/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

C31-Grill

启动前、决策前、或任何涉及 ≥2 文件修改 / ≥2 小时投入的任务前,对计划或设计进行 relentless interview。逐层拷问,直到 C31 与 Chian 达成共享理解(shared understanding)。

基于 Matt Pocock 的 grill-me + grill-with-docs + domain-modeling 三个 skill 的融合。 grilling 过程自动做 domain modeling——不需要手动触发,不需要区分模式,C31 在追问过程中自然检测、确认、建档。

原始核心 Prompt(保留,不改动)

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.

If a question can be answered by exploring the codebase, explore the codebase instead.

自动 Domain Modeling( grilling 过程内置)

grilling 过程中,C31 自动检测以下三种信号,实时追问确认,并写入文档。不需要手动触发,不需要用户说"grill-with-docs"。

信号一:新术语 / 模糊词汇

检测时机:用户使用了现有 memory/glossary.md 中没有的术语,或使用了已被定义但含义不同的词汇。

C31 行为

  1. 立即追问:"你刚才说的'XX',指的是 A 还是 B?"
  2. 用户确认后 → 立即写入 memory/glossary.md
  3. 格式:
    ## XX
    - 定义:{用户确认的精确含义}
    - 首次出现:{YYYY-MM-DD} in {grill session topic}
    - 注意:{与常见用法的区别,如果有}
    

反例:不要等 grilling 结束再批量写。术语确认后 5 秒内就写,否则用户会忘记当时的精确含义。

信号二:关键决策

检测时机: grilling 过程中,用户做出了一个涉及选择、取舍、或不可逆的决策。

C31 行为

  1. 追问:"为什么选 A 而不是 B?"
  2. 如果满足 ADR 三条件(难反转、未来会奇怪、有真实权衡)→ 追问"你的权衡点是什么?"
  3. 用户确认后 → 立即写入 memory/decisions/YYYY-MM-DD-{topic}.md
  4. 格式:
    # ADR: {决策标题} | {date}
    
    ## 背景
    {grill 过程中用户描述的问题}
    
    ## 决策
    {用户最终确认的选项}
    
    ## 权衡
    - 选项 A:{优点} / {缺点}
    - 选项 B:{优点} / {缺点}
    - 为什么选这个:{用户给出的理由}
    
    ## 后果
    - 积极:{预期好处}
    - 风险:{如果后悔,代价是什么}
    

ADR 三条件(满足任意一个就写):

  1. 难反转 — 改主意后需要大量返工
  2. 未来会奇怪 — 三个月后的自己会问"为什么选这个?"
  3. 有真实权衡 — 不是"只有这个能用",而是"几个选项中选了它"

信号三:与现有记忆冲突

检测时机:用户说的内容,与 memory/AGENTS.md 中已有的记录矛盾。

C31 行为

  1. 立即指出:"你之前定义'XX'为 A,现在似乎在说 B,哪个对?"
  2. 不假装没发现。冲突是最高质量的 grilling 信号。
  3. 用户确认后 → 更新 glossary 或标记旧决策为 deprecated

写入位置(严格分层,防止膨胀)

内容类型 写入位置 为什么不是 AGENTS.md
术语定义 memory/glossary.md 术语表独立维护,AGENTS.md 不需要重复
决策记录(ADR) memory/decisions/YYYY-MM-DD-{topic}.md 决策日志是高频文件,AGENTS.md 是低频协作规则
完整共识 memory/grill-sessions/YYYY-MM-DD-{topic}.md 归档用途, grilling 结束后汇总输出
协作规则更新 AGENTS.md 极少——只有发现规则明显缺失/矛盾时才更新,且需用户确认

Read the full file on GitHub · 219 lines

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. 8d ago First seen · 219 lines · 54 tokens per session scan A 85c230a0d1f1

Subscribe to this mod's changes

C31-grill is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 13d ago), licensed MIT. It adds 54 tokens to every session and 2,705 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

compare-harnesses

Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.

ruvnet/metaharness · 66 tokens

oia-manifest

Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.

ruvnet/metaharness · 79 tokens

create-harness

Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…

ruvnet/metaharness · 89 tokens

diag-harness

Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.

ruvnet/metaharness · 85 tokens

example-harness

Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…

ruvnet/metaharness · 90 tokens

repo-genome

7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.

ruvnet/metaharness · 73 tokens