Borrowing it
Nothing to install: this file belongs to LUKAWI/super-plumber. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LUKAWI/super-plumber/master/.pi/skills/sp-grilling/SKILL.mdgit clone --depth 1 https://github.com/LUKAWI/super-plumberWrote 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/lukawi/super-plumber/sp-grilling)<a href="https://agentmods.dev/skills/lukawi/super-plumber/sp-grilling"><img src="https://agentmods.dev/badge/skills/lukawi/super-plumber/sp-grilling.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 | $0.00084 | $0.01413 |
| Opus 5 | $0.00042 | $0.00707 |
| Sonnet 5 | $0.00017 | $0.00283 |
| Haiku 4.5 | $0.00008 | $0.00141 |
Grade A, and why
sp-grilling 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 yesterday.
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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SP Grilling — 纪律技能：一次一问的意图对齐与决策拷问
Overview
- 定位：SP 自带纪律技能族成员（DEC-6 ③，adr_0014 的 skill 面）——MP grilling 本体的忠实移植 + SP 落点附录。工作流全周期的统一对话核心：需求与方向对齐、serve 人审对图质检、开发中决策、改决定、成品审核。
- 仅用户主动调用：不由 agent 或其它 skill 自动接入。普通需求澄清、设计审核不等于开启 grilling；本技能不是审核前置门禁。仍不单独分发 command。
- 本页结构：本体协议（忠实移植，勿改）→ 强度分档 → SP 落点附录（共识后的结论如何落图）。
本体协议（一次一问，直到共识）
- 无情访谈到共识：就当前的计划/决策/想法的每一个方面对我无情追问，直到我们达成共识的理解。沿决策树的每个分支走下去，把决策之间的依赖逐一解开。每个问题都附上你的推荐答案。
- 一次一问：一次只问一个问题，等我给出反馈后再继续。一次抛出多个问题令人不知所措。
- 事实自查，决策归人：凡是能通过探查环境查到的事实（文件系统、graph CLI/MCP 工具、代码、图内状态），自己查，不要问我；决策是我的——把每一个决策摆到我面前，等我的答复。
- SP 语境对照——事实：某节点当前状态、某 ADR 是否已 superseded、validate 是否 0 error、某文件是否存在；决策：节点该拆还是该合、ADR 够不够三判据、任务定 quick 还是 standard、方案选哪条。
- 共识前不动手：在我确认我们已达成共识之前，不要动手执行任何落图/改图/施工动作。
强度分档
| 档位 | 何时用 | 深挖强度 |
|---|---|---|
| quick 轻量档 | 经 plumber-design Phase 0 路由定档为 quick 的任务 | 少轮次：只对齐目标与验收各一问（附推荐答案），不逐分支深挖；两问得到答复即共识 |
| standard / program | 其余全部（含路由不明的任务） | 全量深挖：本体协议逐条走满——决策树逐支、依赖逐一、每问附推荐答案，直到共识闭合 |
档位不明确时按高档执行：宁可多问，不可漏问。
雾区豁免（IL-026；依据 adr_0007：雾区只提示不阻止）：对图上登记了雾区（fog）的点位，只拷问一问——「毕业条件（graduation）是否可验证/可观测」，不按 standard 档粒度逐支深挖：认知未到处不假装精确，雾区内部的问题留待 research 解雾后再拷。话术互指：雾区在 web-ui serve 的 chart 模式可见，毕业走 graph graduate-fog（手册 §2.2）。
SP 落点附录：访谈结论四路落图
本体协议跑完、共识达成之后，把结论按性质路由到 SP 资产落位。路由只在共识后追加落图动作，不改变本体协议本身：
- 工作类定档（这个活是什么量级）→ 回 plumber-design Phase 0 路由表顺序定档：关键未知阻止形成可信交付计划则 program；否则按一个会话能否完成并验收选 quick / standard，跨会话或跨图不单独触发 program（DEC-2）：
.pi/skills/plumber-design/SKILL.md。 - 设计决策（难逆转 + 脱离上下文令人费解 + 真实权衡，ADR 三判据全满足）→
graph adr create落 ADR 顶点（状态 proposed，accept/supersede 裁决归 Super Mario/人类），再以 decides 边挂到管辖的节点/context。 - 改决定（图已画好要改）→ 按 DEC-7 改图协议分流：
- 小修（不动结构：节点 plan/DoD 文案、checkpoint 增删）→ 归 plumber-execute 上报出口（WF16）：worker 提议、执行报告注明"计划已修订"；
- 结构修订（增删节点/边、拆分节点、取消子树、ADR supersede 连锁失效）→ 归 designer amend 模式（增量 validate + 影响评估 + 增量人审）；执行者不自己改结构。
- 审批对话（serve 人审中或审核结论）→ DEC-1 凭据话术：用户批准后由 designer 调一次
graph approve --by <审核者>落审批凭据（quick 档 init 后自签）；对话本身仍按本体协议走，凭据是落点不是替代。
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.
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.
- yesterday Changed · -107 tokens per session 68c06caf6977
- 4d ago Changed · +2 lines 42ed27e4f2d0
- 8d ago First seen · 45 lines · 191 tokens per session scan A dec39e0c6a5d
sp-grilling is a skill published in the GitHub repository LUKAWI/super-plumber (3 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 1,413 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…