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 skills/superman1006/meetmind/project-flow-analyzernpx skills add superman1006/MeetMind --skill project-flow-analyzergit clone --depth 1 https://github.com/superman1006/MeetMindWrote 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/superman1006/meetmind/project-flow-analyzer)<a href="https://agentmods.dev/skills/superman1006/meetmind/project-flow-analyzer"><img src="https://agentmods.dev/badge/skills/superman1006/meetmind/project-flow-analyzer.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 | $0.00157 | $0.01330 |
| Opus 5 | $0.00078 | $0.00665 |
| Sonnet 5 | $0.00031 | $0.00266 |
| Haiku 4.5 | $0.00016 | $0.00133 |
Grade A, and why
project-flow-analyzer scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 标准库 / 第三方库 → 标注一下用了什么就停（例如 `requests.get(url)`、`json.loads(text)` 不再展开内部） How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Flow Analyzer
1. 何时触发本 skill
用户的请求满足以下任一意图时使用：
- 分析项目调用流程、调用链、调用关系
- 从入口（main / cli / entrypoint）开始展开看"谁调用了谁"
- 画项目结构图、架构图、流程图、调用图
- 可视化项目、展示模块/函数关系
如果用户的话只是要"看代码"或"读文件"——不是要看关系/调用链——不要触发本 skill。
2. 工作流
Step 1: 找入口
按项目类型确定入口文件 + 入口函数：
| 项目类型 | 常见入口 |
|---|---|
| Python (CLI) | main.py、__main__.py、<pkg>/cli/main.py、pyproject.toml 的 [project.scripts] |
| Python (lib) | 用户指定的目标函数，或 __init__.py 暴露的主接口 |
| Python (Web) | app.py、wsgi.py、manage.py，框架的 create_app() |
| Node | package.json 的 main / bin、index.js |
| Go | main.go 的 func main() |
| Rust | src/main.rs 的 fn main() |
| Java | 含 public static void main 的类 |
如果用户没指定，先 grep 确认，不要凭名字猜。
Step 2: 递归展开调用
从入口函数开始，逐层展开它调用的函数 / 类 / 方法。对每个被调用的对象记录：
- 文件路径（相对项目根，例如
meetmind/agents/base.py） - 函数/方法名（如
BaseAgent.process） - 关键参数（只列必要的，类型可选）
- 一句话职责
展开规则：
- 项目自身的函数 → 展开
- 标准库 / 第三方库 → 标注一下用了什么就停（例如
requests.get(url)、json.loads(text)不再展开内部） - 工厂函数 / 一行 wrapper → 跳过中间层，直接展开它的产物
- 控制流（
while True:、for ... in ...）→ 用箭头或[/伪代码/]表示，不要漏掉
禁止凭训练数据猜：每条 (path/to/file.py) 都必须是用 Read 或 Grep 实际验证过的真实路径。
Step 3: 输出
默认输出 = 层级缩进的文字版调用链。用户绝大多数情况只要这个：
入口
├─ 第一层函数A() (path/to/file.py)
│ ├─ 第二层函数B(arg1, arg2) (path/to/another.py)
│ │ └─ 第三层函数C() (path/to/third.py)
│ └─ 第二层函数D() (path/to/another.py)
└─ 第一层函数E() (path/to/file.py)
格式要点：
- 用
├─ └─ │树形字符（不要用纯空格缩进，可读性差） - 每行末尾对齐
(文件路径) - 控制流用
【for each x: …】或【while True:】包起来 - 跨章节用
---横线或 emoji 标题（如## 🤖 内部循环）分块
只在用户明确说 "画图 / HTML / mermaid / 可视化 / 流程图 (要图形版)" 时输出 HTML：
- 单文件 HTML，CDN 加载 mermaid
- 必须遵循
references/mermaid-pitfalls.md里的全部规则，否则会渲染失败 - 生成后告诉用户文件路径 + 直接用
open命令打开
3. 工具选择
- Explore agent（不是 general-purpose）：找入口、grep 调用关系、找类定义。Explore 是只读、专门干这个的。
- Read：知道路径后读完整文件
- Grep：搜索
def func_name、func_name(、import X等 - 不要凭训练数据：每条调用关系都要在代码里确实存在。如果一个函数的实现你猜不出来，就 Read 它再写。
What ships with it
2 files 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.
- 5d ago First seen · 98 lines · 157 tokens per session scan A 33602bd33af6
project-flow-analyzer is a skill published in the GitHub repository superman1006/MeetMind (57 stars, last pushed 2mo ago), licensed MIT. It adds 157 tokens to every session and 1,330 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…