Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/KhazixW2/Everything-Maanpx agentmods add skills/khazixw2/everything-maa/maa-pipeline-graphWrote 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/khazixw2/everything-maa/maa-pipeline-graph)<a href="https://agentmods.dev/skills/khazixw2/everything-maa/maa-pipeline-graph"><img src="https://agentmods.dev/badge/skills/khazixw2/everything-maa/maa-pipeline-graph/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/khazixw2/everything-maa/maa-pipeline-graph"><img src="https://agentmods.dev/badge/skills/khazixw2/everything-maa/maa-pipeline-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00131 | $0.03430 |
| Opus 5 | $0.00066 | $0.01715 |
| Sonnet 5 | $0.00026 | $0.00686 |
| Haiku 4.5 | $0.00013 | $0.00343 |
Grade A, and why
maa-pipeline-graph 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 10d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline 状态机图谱生成
项目初始化接力
画图前先查目标根目录的 basic_info.md。存在且包含第 0 节时,读取“0. Maa Skills 接力协议”和第 2/3/6 节,把 task entry、Pipeline 文件清单、JSON 边与 Python 外部入口作为图谱种子;随后仍须扫描当前主 interface.json / interface.jsonc、其 import[]、每个 resource[].path 声明资源根内的 Pipeline,以及 agent/**/*.py 的 run_task() / run_recognition(),不能把缓存当完整图数据库。文件缺失或没有第 0 节时直接扫描当前项目;不得自动调用 $maa-project-init,只有用户明确要求初始化或刷新时才调用。源码比文档新时以源码为准并报告缓存过期,不自动刷新或覆盖已有非空文档。
TL;DR
把"声明式 JSON 节点 + 命令式 Python 调度"的项目(Pipeline 节点 + context.run_task() / context.override_pipeline() 调用 + option/task 入口)整理成状态机图或关系表。
先发现真实工具,不要假设脚本存在。历史审查发现 MaaGumballs 计划中提到的 tools/pipeline_to_mermaid.py 在目标提交并不存在;因此本 skill 不能默认承诺一键运行该脚本。
rg --no-ignore --files -g '!.git/**' -g '!.venv/**' |
Where-Object {
[IO.Path]::GetFileName($_) -match
'pipeline.*(mermaid|graph)|(mermaid|graph).*pipeline|migrate_pipeline'
}
- 如果仓库已有图谱脚本,先读脚本参数再运行。
- 如果没有脚本,只做分析、临时 Mermaid 草图或工具设计建议,不要声称生成了持久化图谱工具。
- 任何 HTML/图谱产物都应输出到已忽略目录,或先确认
.gitignore。
When to use
- 理解陌生项目:新接手一个 MaaFramework 项目,想一眼看清节点、调用、入口
- 重构前盘点:大改某个 Pipeline 文件前,先看图,免得改完不知道影响了哪些边
- 调试"孤儿"节点:某节点在 Pipeline 里没
next指向它,想知道是 bug 还是被 Python 调用 - 加新节点后:新加了一个 Pipeline 节点或
run_task调用,刷新图看新边 - Code review:看 PR 时,先看图理解结构再看代码,效率翻倍
- 写文档 / 培训新人:把图当 on-boarding 资料
What it can produce
如果项目已有图谱脚本,通常会产出这些文件;如果项目没有脚本,本 skill 只负责设计这些产物或生成临时草图,不默认创建工具:
| 文件 | 用途 | 语法 |
|---|---|---|
index.html |
主目录(卡片导航 + 全局统计) | HTML 卡片 |
pipeline_overview.html |
全局状态机,按实际文件数生成复合状态 | stateDiagram-v2 |
pipeline_external_entries.html |
Python → Pipeline 调用图 | flowchart |
pipeline_utility_usage.html |
工具节点反向引用图 | flowchart |
pipeline_<file>.html × N |
每个实际 Pipeline 文件的状态机细节 | stateDiagram-v2 |
多文件图谱应带顶部导航栏和主页;是否支持 --open / --watch 取决于真实脚本能力。
How to use
发现并运行现有工具
rg --no-ignore --files -g '!.git/**' -g '!.venv/**' |
Where-Object {
[IO.Path]::GetFileName($_) -match
'pipeline.*(mermaid|graph)|(mermaid|graph).*pipeline|migrate_pipeline'
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 243 lines · 131 tokens per session scan A 78055c881a42
maa-pipeline-graph is a skill published in the GitHub repository KhazixW2/Everything-Maa (12 stars, last pushed 2d ago), licensed MIT. It adds 131 tokens to every session and 3,430 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.
atmos-schemas
JSON Schema for Atmos: stack-manifest and atmos.yaml config schemas, IDE auto-completion, validate stacks/schema/config, SchemaStore integration.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
openocd
A toolkit for programming and debugging microcontrollers through hardware probes such as ST-Link or CMSIS-DAP. OpenOCD can act as a GDB Server, allowing a debugger to inspect source code, registers, memory, breakpoints, and program execution.