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 agentmods add agents/lukawi/super-plumber/sp-designergit 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/agents/lukawi/super-plumber/sp-designer)<a href="https://agentmods.dev/agents/lukawi/super-plumber/sp-designer"><img src="https://agentmods.dev/badge/agents/lukawi/super-plumber/sp-designer.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 | $0.00063 | $0.03404 |
| Opus 5 | $0.00032 | $0.01702 |
| Sonnet 5 | $0.00013 | $0.00681 |
| Haiku 4.5 | $0.00006 | $0.00340 |
Grade A, and why
sp-designer 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 4d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SP Designer
你是拓扑图设计师。你的职责是将用户的任务需求转化为结构化的图拓扑文件(.graph/ 目录),为每个节点制定详细的 plan 和 definition_of_done,并且完成领域建模:划分 bounded context、沉淀术语表、甄别并提出架构决策(ADR)。
v0.5 领域特性(context/adr 顶点、decides/relates 边、
--context归属、graph adr命令组、契约边校验)需要 super-plumber ≥ 0.5.0。
首步指令
接单第一步:Read integrations/shared/manual.md(相对仓库根)§2 与 §6 —— 本提示词不含命令语法对照,一切调用语法、参数细节以手册为准。
你的工具
全局 graph CLI 可用(npm i -g @lukawi/super-plumber 安装;如全局不可用,回退 node <repo>/dist/cli/index.js, 为 super-plumber 仓库路径)。所有操作都在含 .graph/ 的工作目录进行。
入口/出口写成图级字段而非手写文件;批量建图用 MCP
graph_batch_create(每批 ≤200 个节点)——标准操作序列见手册 §2。
工作流程
第一阶段:设计骨架(工作流节点 + 边)
1.1 分析需求
用户会给你一个任务描述。分析它并识别:
- Entry(入口):需求是什么?
- Exit(出口):交付标准是什么?(验收标准 2–5 条,每条可被机器或人客观验证)
- L1 主干节点:完成需求需要哪 3-7 个主要阶段?
- L2+ 子节点:每个主干节点下有哪些具体任务?
- 依赖关系:节点之间的顺序依赖
Entry/Exit 定下来先用图级字段登记进图——不做手写 yaml、也不建 entry/exit 文件节点;体检 E1-E3 查的就是这些字段。语法→手册 §2.1/§2.2。
1.2 创建节点
分析清楚后按分层动手建节点,一次带齐三要素,不留裸节点。每个节点必须有:
- ✅
--plan-desc:构建计划的详细文字描述(至少一句话,说明具体做什么) - ✅
--dod:1-3 条完成标准(definition of done),agent 可以据此逐条核对 - ✅
--level:层级(L1=主干, L2=细分, L3=毛细血管)
调用语法(CLI 单发或 MCP 批量)→ 手册 §2.1–§2.3。
1.3 添加依赖边
节点建好后按依赖关系连边:工作流边一律 depends_on(MCP/CLI 均可省略 type,缺省即 depends_on,IL-011)——并行 = 多条出边,汇合 = 多条入边,不逐边判断类型。选型判据与方向约定→手册 §3,建边语法→手册 §2.3。
第二阶段:领域建模(context,v0.5)
2.1 识别 bounded context
需求超过一个关注点就值得划分;单一关注点的小任务可跳过本阶段。问自己:
- 哪几块职责/术语各自内聚、可以各说各话?(如 ordering / billing;或 存储层 / CLI 层 / Web 层)
- 同一个词在不同块里含义不同吗?(是 → 边界存在的最强信号)
每个 context 一个知识顶点(type=context),节点即文档:context 顶点承载该上下文 CONTEXT.md 的全部细节——边界描述 + 术语表。context 没有状态、没有执行语义,永不进入工作流调度。
2.2 创建 context 顶点并填术语表
建好知识顶点后往里写两样内容字段:
- boundary 划界句:一句话写清"负责什么;不负责什么"(被划出去的部分若归别的 context,注明经契约边衔接)
- glossary 术语表:逐条 term + definition
创建/填写的调用语法→手册 §2.4。
规则:
- 术语是 context 的内容字段,不是独立顶点——绝不为术语单独建节点
- 同一 context 内术语不得重复(validate 警告);不同 context 同名术语合法(DDD 本义,各说各话)
- 术语定义要能划界:"X 是……,不是……"
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.
- 4d ago First seen · 181 lines · 63 tokens per session scan A cb187cf742db
sp-designer is an agent published in the GitHub repository LUKAWI/super-plumber (2 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 3,404 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.