super-plumber: Skill for Claude Code

.pi/skills/plumber-execute/SKILL.md

plumber-execute is a skill for Claude Code, Codex from LUKAWI/super-plumber. It costs 152 tokens per session (3,583 once invoked), scanned A, original, MIT.

A guided execution skill for running an approved task topology, a dependency map of work, from start to finish. It claims tasks, performs them, reports checkpoints, and verifies the final result.

In plain words
What is it for?
Use it after a topology has been designed and approved to execute its nodes, coordinate subagents or solo work, retry failures, and confirm the finished build.
Why use it?
It provides a controlled process for executing tasks in order and handling parallel work or failures. It separates approved planning from implementation and final checks.

Skill for Claude CodeCodex

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

This is LUKAWI/super-plumber's own configuration. It tells Claude Code and Codex how to work on super-plumber itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything super-plumber configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/LUKAWI/super-plumber/master/.pi/skills/plumber-execute/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/LUKAWI/super-plumber

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 plumber-execute

README.md
[![agentmods](https://agentmods.dev/badge/skills/lukawi/super-plumber/plumber-execute/github.svg)](https://agentmods.dev/skills/lukawi/super-plumber/plumber-execute)
Your own site
<a href="https://agentmods.dev/skills/lukawi/super-plumber/plumber-execute"><img src="https://agentmods.dev/badge/skills/lukawi/super-plumber/plumber-execute/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 plumber-execute

Your own site · 80×15
<a href="https://agentmods.dev/skills/lukawi/super-plumber/plumber-execute"><img src="https://agentmods.dev/badge/skills/lukawi/super-plumber/plumber-execute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,583 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 $0.00152 $0.03583
Opus 5.5 $0.00061 $0.01433
Sonnet 5.5 $0.00030 $0.00717
Haiku 4.5 $0.00015 $0.00358

Measured 1mo ago against content hash 2a7d2a0119ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plumber-execute 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 1mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/sp-check-design.mjs, scripts/sp.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.pi/skills/plumber-execute/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plumber Execute — 主线程编排剧本:拓扑执行 → 全部 passed → 三层验收

Overview

按依赖顺序执行每个节点:CLAIM → WORK → 逐 checkpoint 上报 → execution_report → passed;全部 passed 后做三层验收,验证构建成果真实完整。本页是编排剧本:每步只留一句纪律,全部调用语法、字段含义与报错修法统一看 Operations 手册(寻址约定见手册 §11);细则按需读 attachments/(与本文件同目录,两渠道同构可解析):context-hygiene / prototype-research(chart/work 两模式细则在 plumber-design 附件 wayfinder-mode)。产出物 = 全部节点 passed 且验收通过的构建成果,不是设计;图还没设计/未审核 → 回 plumber-design。

When to Use 与衔接关系

  • Use:拓扑图已设计并审核通过,开始执行节点任务;claim / checkpoint / execution_report / 状态流转;判断串行还是派 subagent 并行;验证全部节点 passed、构建成果完整;节点 failed → 走重试链重新调度。
  • 代理层级边界:skill 文本和“有 subagent 工具”都不能可靠识别代理深度,故每个会话默认无派单权,不得从能力存在推断授权。只有直接承接用户执行请求的外层协调者可持一次性、不可转授的 orchestrator 授权直接派 executor;授权在派发时耗尽,子任务只收到 leaf 约束,绝不可向下复制。缺授权一律 solo。当前通用宿主未向 skill 暴露可验证的签名层级令牌,因此这是行为协议而非硬隔离:需要强保证的宿主还必须在工具层移除子 agent 的派发能力。
  • 执行协议的工具调用语法与并行数据判读法 → 手册 §4;状态机七态与三条硬规则 → 手册 §5——本 skill 只留骨架与纪律,绝不复述语法。
  • 图未设计或未审核通过 → plumber-design;节点状态裁决 / checkpoint 聚合 / 输出抽查 → super-mario agent;派 executor subagent → 按「派单模板」,检测不到可用 subagent → 走「solo 分支」;新会话缺少背景 → /plumber-join 获取最小上下文并置 ready 后回本技能;已有上下文直接执行,不重复入场。

执行协议(每节点 0–5 步,严格按序;各步调用语法统一 → 手册 §4.1)

  1. PLAN — 每轮决策前先看 graph_get_next_actions 五桶;优先已有 ready 节点,空时再从 ready_eligible 选择(门禁复校后转 ready),不要拿 get_graph+search 手工拼数据。
  2. CLAIM — 只 claim ready 节点(eligible 先 {status:"ready"} 再 claim),必带 claim_by,拿到 already claimed 就换节点别重试同节点;claim 响应附 governing_adrs 必读——adr_flags ⚠️ 出现即停:该节点依据的 ADR 已被接替,先弄清新决策再动手,ADR 状态只能由裁决方(super-mario/人类)改。
  3. WORK — 执行 plan.description,把 checkpoints 当逐条清单完成。测试先行、新增测试或缺陷修复 → 若可用,参考 plumber-tdd;遇到 cross_review 或指定 artifact 复核 → 若可用,交 plumber-review,结果交 super-mario/独立裁决方。两者都是软路由:技能缺失直接按 plan/DoD 与手册执行,不另找替代、不增加门禁;缺技能不取消原有交叉复核要求,独立复核者不可用时如实交接。
  4. REPORT AS YOU GO — 每完成一个 checkpoint 立即上报,绝不攒批——完成的未上报 = 丢失的进度。
  5. HAND OFF — 干完立刻填 execution_report:artifacts 只写真实文件路径(会被存在性核验),绝不编造路径。
  6. passed — 委派工人止于 report,由 super-mario/独立裁决方写 verdict 并流转 passed;solo 按下文裁定边界处理。核心层硬门禁一句话:非空 report + checkpoint 全 passed/skipped + 无 failed 裁决,缺一即拒——铁律先 verdict 后 passed(重试链 / attempts 上限 / blocked 解除 / reclaim 细节 → 手册 §4.3 与 §5)。

Read the full file on GitHub · 102 lines

Files

What ships with it

5 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. 1mo ago Changed 2a7d2a0119ff
  2. 1mo ago Changed · -57 lines 8ae297b65594
  3. 1mo ago Changed · +30 lines 4c334036eba8
  4. 1mo ago First seen · 129 lines · 152 tokens per session scan A 825c822cf466

Subscribe to this mod's changes

plumber-execute is a skill published in the GitHub repository LUKAWI/super-plumber (3 stars, last pushed 1mo ago), licensed MIT. It adds 152 tokens to every session and 3,583 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…

vercel/next.js · 123 tokens