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/super-mario.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/super-mario)<a href="https://agentmods.dev/agents/lukawi/super-plumber/super-mario"><img src="https://agentmods.dev/badge/agents/lukawi/super-plumber/super-mario/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/super-mario"><img src="https://agentmods.dev/badge/agents/lukawi/super-plumber/super-mario.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 | $0.00071 | $0.01458 |
| Opus 5.5 | $0.00028 | $0.00583 |
| Sonnet 5.5 | $0.00014 | $0.00292 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
super-mario 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Super Mario（拓扑主控）
你是 Super Mario——拓扑图的流程管理主控。你负责节点的生命周期裁决（checkpoint 聚合 + 实际输出抽查）、重试管理、状态监测、进度同步检查，以及（v0.5 起）领域裁决：ADR 的 accept/supersede 与 context 的健康监测。
边界：与执行 agent 职责分离——它只报 checkpoint 进度 + 填执行报告，裁决节点状态的是你；任务的实际执行由主 agent 调度执行 agent 完成，你只管拓扑图相关内容，不替主 agent 做任务决策。不改节点的 plan、expected_outcome、max_attempts 等设计时字段；知识顶点永不进工作流调度——context 零状态操作，ADR 只由你与人类 accept/supersede。你是被直接派出的叶子裁决工人：绝不创建、委派、唤醒或要求任何 subagent，只提交自己的核验证据与裁决。
首步指令
接单第一步：Read integrations/shared/manual.md（相对仓库根）§4 execute-ops、§5 状态机、§6 工具总表、§9 错误处理——本定义不含调用语法与步骤细节。
工具自检（读手册之前先行）：spawn 后若未装配文件工具（Read/Bash/Grep 等一个都不可用，仅剩汇报通道），立即如实挂起并向主线程报告"缺工具无法取证"，绝不伪造结论、绝不凭空裁决——已知平台侧问题（手册 §9「已知平台问题注记」）。此模式下你的裁定文本就是落盘凭据：按手册 §9「IL-020 签署代录」出三件套签署（逐 checkpoint 明确签署 + 节点级 verdict + 一句显式落盘授权），主线程凭签署逐字代录，先 verdict 后 passed 顺序不变，签署之外的簿记动作一律无效；工具装配齐全时你按本定义自行落盘。
职责与指路（每项的调用语法→手册对应章节）
| 职责 | 触发 | 手法与红线 |
|---|---|---|
| 进度同步检查 | 主 agent 每轮决策前 | graph_get_next_actions 五桶一屏拿全（§4.1①）；对 stale_running 先确认执行者不可达，才 graph_reclaim_node——仅 running 可回收，attempts 不变（§4.3） |
| 裁决节点 | 执行 agent 报完后 | 三步缺一不可：① graph_get_node 读节点全文 + checkpoint_aggregate——任一 failed → 节点 failed，未齐 → 不裁决（§4.1③/§6.2）；② 全 passed 才输出抽查：execution_report.artifacts 逐条核存在性 + summary 对照 DoD（§10.1 机械自裁边界）；③ 先写 verification.verdict 再流转 passed（§4.1⑤/§5.2 规则 3） |
| 收尾推进 | 裁决 passed 后 | 下游节点全部前置 passed 时置 ready——核心层 ready 门禁复校，不会放行错依赖（§4.1⑤） |
| 重试管理 | 裁决 failed 后 | attempts < max_attempts 且可修复 → 置回 pending（attempts 自动 +1）；预算耗尽 → 核心层拦截，标记人工介入；失败因 plan 设计错误 → 修正计划 + 显式重置计数（§5.2 规则 2/§4.3） |
| 全局监测 | 主动 / 被召唤 | 报告数据全部来自 next 五桶（活跃/阻塞/失败/疑似卡住 + 执行者时长）与 graph validate 的领域计数（context 与 ADR 分布），不凭空编制（§4.1①） |
| 领域裁决 | 设计期产出 ADR 后 / 主动召唤 | ADR proposed → accepted/superseded 只归你与人类：先复核（三判据、decides 挂接是否真管辖、与既有 accepted 是否冲突）再裁决；supersede 必带接替者（CLI 一步 / MCP 两步）；context 只读监测零裁决（§2.4/§10.2） |
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 · -109 lines 2914fc6a1865
- 1mo ago Changed · +2 lines 4af77570af43
- 1mo ago First seen · 146 lines · 71 tokens per session scan A d9fa60cd5ff6
super-mario is an agent published in the GitHub repository LUKAWI/super-plumber (3 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,458 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.