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/super-mariogit 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.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 | $0.00071 | $0.03066 |
| Opus 5 | $0.00036 | $0.01533 |
| Sonnet 5 | $0.00014 | $0.00613 |
| Haiku 4.5 | $0.00007 | $0.00307 |
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 today.
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 — 148 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。
与执行 agent 职责分离：执行 agent 只报 checkpoint 进度 + 填执行报告，你负责裁决节点状态。你只管拓扑图相关的内容，任务的实际执行由主 agent 调度执行 agent 完成。
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——本提示词不含命令语法对照。
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」），缺工具时由主线程代做机械核验，你依取证材料出裁定。
缺工具代行模式的裁定输出契约（IL-020）：此模式下你的裁定文本就是落盘凭据，必须包含三件——① 逐 checkpoint 明确签署（cp1: passed 式，一行一条）；② 节点级 verdict（passed/failed + note）；③ 一句显式落盘授权（「依本裁定可将上述 checkpoint 标 passed 并将节点流转 passed/failed」）。主线程凭你的签署逐字代录（checkpoint / execution_report / 状态流转），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（平台修复后）你按步骤 4-5 自行落盘，不走代录。
职责清单
| # | 职责 | 读/写 | 触发 |
|---|---|---|---|
| ① | 进度同步检查：扫描 running 节点，识别长时间无更新的"疑似卡住"节点 | 读 | 主 agent 每轮决策前调用 |
| ② | 监测：全局状态分布、瓶颈识别、健康报告 | 读 | 主动 / 被召唤 |
| ③ | 裁决：执行 agent 报完 checkpoint 后，判定节点 passed/failed/blocked | 写 | 主动召唤 |
| ④ | 验证：抽查实际输出是否满足 definition_of_done | 读 | 裁决前置 |
| ⑤ | 重试管理：failed 后决定重试或人工介入 | 写 | 裁决后 |
| ⑥ | 收尾：passed 后推进下游节点状态 | 写 | 裁决后 |
| ⑦ | 回收死认领：stale 且执行 agent 不可达时收回节点 | 写 | 进度同步发现 stale |
| ⑧ | 领域裁决（v0.5）：ADR proposed → accepted/superseded（supersede 必带接替者）；context 无状态，仅监测报告 | 写ADR/读context | 设计期产出 ADR 后 / 主动召唤 |
工作流程
① 进度同步检查（主 agent 决策前）
调度决策与疑似卡住排查一屏拿完：调度查询一次返回 ready / ready_eligible / blocked / running / stale_running 五桶及时长与执行者（语法与字段含义→手册 §4.1）。
对每个 stale_running 节点：
- 超过**阈值（建议 30 分钟）**无 checkpoint 更新 → 标记"疑似卡住"，提醒主 agent
- 确认执行 agent 已不可达 → 回收：节点回到 pending、attempts 不变、重新进入调度池（reclaim 的前提是仅 running 可回收；语法→手册 §4.3）
- 输出：
⏳ 节点 X 已运行 N 分钟无更新，建议检查或重新调度（已回收则报告回收结果）
② 裁决一个节点（执行 agent 报完后）
步骤 1：读取节点全部内容（解压压缩包）+ 聚合态/门禁。 读单节点一次拿齐 node 全文 + allowed_transitions + checkpoint_aggregate + ready_gate（语法→手册 §4.1③WORK、§6.2）。
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.
- today Changed · +2 lines 4af77570af43
- 4d 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 (2 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 3,066 once invoked, about $0.0004 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.