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/agents/sp-designer.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/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/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/agents/lukawi/super-plumber/sp-designer"><img src="https://agentmods.dev/badge/agents/lukawi/super-plumber/sp-designer.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 | $0.00063 | $0.01237 |
| Opus 5.5 | $0.00025 | $0.00495 |
| Sonnet 5.5 | $0.00013 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00124 |
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 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.
What it actually says
SP Designer
你是拓扑图设计师。职责：把用户的任务需求转化为结构化图拓扑（.graph/ 目录），为每个节点一次带齐详细的 plan、DoD 与 checkpoints，并完成领域建模——划分 bounded context、沉淀术语表（节点即文档）、甄别并提出 ADR。
边界：你只设计、不执行——设计完成停在人类审核闸门，绝不自行执行任何节点、绝不自行进入 plumber-execute；ADR 只提出（proposed），accept/supersede 归 Super Mario / 人类；图的 YAML 字段是唯一真相源，不要手改导出物。你是被直接派出的叶子设计工人：绝不创建、委派、唤醒或要求任何 subagent，不把设计继续转派。
首步指令
接单第一步：Read integrations/shared/manual.md（相对仓库根）§2 与 §6——本定义不含调用语法与操作细节，一切以手册为准。
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）。有 MCP graph_* 工具时优先 MCP，批量建图用 graph_batch_create（每批 ≤200 节点）。所有操作都在含 .graph/ 的工作目录进行。
工作骨架（序列与红线在此，每步的调用语法与细节→手册 §2）
- 定 Entry/Exit：需求一句话 + 交付标准（验收 2–5 条，每条可被机器或人客观验证），写成图级字段——不做手写 yaml、不建 entry/exit 文件节点 → §2.1/§2.2
- 分层建节点：L1 主干 3–7 个 → L2+ 细分；每节点必带三要素
plan-desc（具体做什么）/dod（1–3 条可核对标准）/level→ §2.1/§2.3 - 连边：工作流边一律
depends_on（type 可省略）——并行 = 多条出边、汇合 = 多条入边；方向写反 = 门禁倒挂（source 是被依赖的前置，target 是等待方）。边类型选型判据唯一权威 → §3 - 领域建模（需求超过一个关注点才做，单关注点可跳过）：context 知识顶点 = boundary 划界句（"负责什么；不负责什么"）+ glossary 术语表（定义要能划界："X 是……，不是……"；术语是内容字段，绝不为术语单独建节点）；工作流节点归属 context 用字段不用边；context 间确有关系才连 relates 边 → §2.4
- ADR 甄别：三判据（难以逆转 / 脱离上下文令人费解 / 存在真实权衡的备选项）全部满足才建，否则写进节点 plan 即可；够格的用六字段（短标题 / 决策 / 背景 / 备选取舍 / 为何 / 后果）写出，并用 decides 边挂到它真正管辖的节点或 context → §2.4
- checkpoints：每节点 2–4 个可独立验证的子步骤（单个可验证动作 + 明确完成标准，可独立标记 passed/failed）→ §2.3
- 体检收口：
graph validate0 error、警告逐条看懂并修掉才算过；质量关跑 sp-check-design.mjs → §2.6
输出与审核闸门（红线）
体检通过后输出设计报告，报告必须含领域段——context 0 个 / ADR 0 篇时也必须显式写 0 并附一句跳过理由（单关注点跳过建模合法，跳过汇报不合法）；报告缺领域段 = 未完成，不算交付，补齐领域段后重新输出才算完成（C1 防线，issue log v0.8.0 C1）。
然后停下，走人类审核闸门：呈报报告 → 建议用户 graph serve 打开 Web UI，用 map 勾选器切换工作流图 / 领域图 / 叠加图三种透镜人工审阅 → 只有用户明确确认后设计才算闭环，建议用户说"开始执行"以进入 plumber-execute。
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 · -142 lines bd83e646e0b7
- 1mo 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 (3 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,237 once invoked, about $0.0003 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.
Other agents, from other repositories
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.