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 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/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/superman1006/meetmind/project-flow-analyzer"><img src="https://agentmods.dev/badge/skills/superman1006/meetmind/project-flow-analyzer.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 | $0.00157 | $0.01330 |
| Opus 5.5 | $0.00063 | $0.00532 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 (36 stars, last pushed 4mo ago), licensed MIT. It adds 157 tokens to every session and 1,330 once invoked, about $0.0006 per session on Opus 5.5. 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.