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 ChianW/C31 --skill c31-grillgit clone --depth 1 https://github.com/ChianW/C31Wrote 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/chianw/c31/c31-grill)<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>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 | $0.00054 | $0.02705 |
| Opus 5 | $0.00027 | $0.01352 |
| Sonnet 5 | $0.00011 | $0.00541 |
| Haiku 4.5 | $0.00005 | $0.00270 |
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.
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:
- 立即追问:"你刚才说的'XX',指的是 A 还是 B?"
- 用户确认后 → 立即写入
memory/glossary.md - 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:
- 追问:"为什么选 A 而不是 B?"
- 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?"
- 用户确认后 → 立即写入
memory/decisions/YYYY-MM-DD-{topic}.md - 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):
- 难反转 — 改主意后需要大量返工
- 未来会奇怪 — 三个月后的自己会问"为什么选这个?"
- 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/ 或 AGENTS.md 中已有的记录矛盾。
C31 行为:
- 立即指出:"你之前定义'XX'为 A,现在似乎在说 B,哪个对?"
- 不假装没发现。冲突是最高质量的 grilling 信号。
- 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 |
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.
- 8d ago First seen · 219 lines · 54 tokens per session scan A 85c230a0d1f1
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.
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.
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.
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…
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.
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…
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.