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/plumber-review/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/plumber-review)<a href="https://agentmods.dev/skills/lukawi/super-plumber/plumber-review"><img src="https://agentmods.dev/badge/skills/lukawi/super-plumber/plumber-review/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.
<a href="https://agentmods.dev/skills/lukawi/super-plumber/plumber-review"><img src="https://agentmods.dev/badge/skills/lukawi/super-plumber/plumber-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00184 | $0.01996 |
| Opus 5.5 | $0.00074 | $0.00798 |
| Sonnet 5.5 | $0.00037 | $0.00399 |
| Haiku 4.5 | $0.00018 | $0.00200 |
Grade A, and why
plumber-review 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.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plumber Review — 纪律技能：节点产物的双轴交叉复核
Overview
- 定位：SP 自带纪律技能族成员（DEC-6，adr_0005）——服务图中节点的交叉复核手法，主要供三层验收成果层与
cross_reviewcheckpoint 使用：对（通常已 passed 的）节点 artifact 做第二双眼复核。无节点归属的全库审计/自由 code review 不适用本页（防蔓延：纪律技能只服务图中节点）。 - 纪律族不发 command（DEC-6 ②）：触达靠触发语自动命中与节点 plan 指针，无斜杠命令、无入口编排。
- 统一入口边界：用户主动要求拷问/意图对齐时路由到 SP 自带
sp-grilling；diagnosing/prototype保留为 1.0.x 后续，本期不新增、不发命令。 - 交叉 = 复核者不是执行者：同一会话给刚写完的东西盖章不算交叉。复核者是编排方指派的另一 agent/会话。
- 本 skill 零派单权：
plumber-review只定义复核方法，绝不创建、委派或要求 subagent。它无法可靠判定当前会话在代理树中的层级，因此所有调用一律按叶子复核会话处理；独立复核的派发只能由本 skill 外持一次性、不可转授orchestrator授权的用户侧协调者直接完成，且该权限不可经本 skill 推断或继承。该协议消除 review 自身的递归触发；若宿主没有在工具层限制子会话派发，则无法把文档约束伪称为硬安全边界。 - 复核与裁决必须分离：reviewer 只做双轴取证，绝不更新 checkpoint、
verification.verdict或节点状态；独立的 Super Mario / 指定裁决者读完 reviewer 的证据后，才可裁决。纯读报告之后若没有独立裁决，就仍是未完成的审核链路。 - 铁律（手册 §8 成果层）：不信报告信 artifact——直接读文件核实；execution_report 的 summary 只是线索，不是证据。
双轴（并行跑，互不污染）
| 轴 | 输入 | 只回答一个问题 |
|---|---|---|
| 规格轴（Spec） | graph_get_node 的 plan + DoD 全文 |
产物是否忠实落实了节点书？逐条 DoD 找可核验佐证；找缺失/走样、计划外夹带（干了 plan 没让干的）、看似做了但实现可疑的点 |
| 惯例轴（Standards） | 节点文件边界、仓库成文纪律（CONTEXT.md 术语、手册红线如「产物禁止手改」「先 verdict 后 passed」、测试基建既有约定） | 产物是否遵守了仓库的成文纪律？违反处引用纪律原文 + 产物位置 |
并行是外层编排，不是本 skill 的动作：需要两名独立复核者时，由用户侧协调者/编排器直接派两个叶子会话，一人只获派规格轴、一人只获派惯例轴；派单必须明写「叶子复核者：不得调用任何 subagent/delegation 工具」。每个叶子只读取这份 skill 并完成自己的一轴，因此不会再派生下一层。plumber-review 自身不因环境存在 subagent 而派人。
solo / 单轴派单：没有外层独立派发时，严格在本会话隔离两遍——先只备惯例轴输入跑完并写下结论，再开规格轴跑第二遍，绝不带着一轴的结论看另一轴；若外层明确只派一轴，则只完成该轴。两轴输入都在开工前各自备齐，中途互不互通。不得为了并行而再派 agent。
结论不合并
两轴结论分开呈现：## 规格轴、## 惯例轴 各列各的发现（每条带引用：DoD/纪律原文 + artifact 文件与引文），末行各给本轴最重问题。不跨轴合并、不再排序、不产出单一总裁决——一轴全绿另一轴有雷是完全可能的结果，分开报告才不让一轴掩盖另一轴。裁决（放行/打回/改 plan）归裁决方，不归本页。
复核者红线
- 不动图状态：reviewer 不得更新 checkpoint、execution report、
verification.verdict或节点状态，也不得代签；绝不触碰执行者已认领的源任务节点、其 checkpoint 或设计字段。发现缺陷或全部通过，都交给独立裁决者。 - 叶子不嵌套：任何复核会话都不得创建、委派、唤醒或要求另一个 agent 继续复核；只读 artifact、完成获派的一轴并把证据返还上层。需要第二轴时由本 skill 外的协调者直接安排，不能经由复核者转手。
- 检查点归属：
cross_reviewcheckpoint 的 passed/failed 由独立裁决者依据 reviewer 报告上报；若源任务需要独立审核状态，由协调者建立 review 节点或提供报告 artifact，不能让 reviewer 越权修改源任务。 - 发现本身要过安检：每条发现给出可复现的核实手法，不凭报告文本断言。
- 修复若涉及新测试/缺陷修复，修复者可参照测试先行纪律——若本环境存在 plumber-tdd 技能，按其约定执行；缺失则静默降级。
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.
- 1mo ago Changed · +1 lines · +10 tokens per session a6e82e1cf2bc
- 1mo ago First seen · 53 lines · 174 tokens per session scan A e2f0480fd8ac
plumber-review is a skill published in the GitHub repository LUKAWI/super-plumber (3 stars, last pushed 1mo ago), licensed MIT. It adds 184 tokens to every session and 1,996 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…