Route ScanningSAFE

This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库,目标就是: 👉 把 Claude Code 从“对话式编码工具”,变成 可设计、可复用、可治理的工程系统。

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: route-scanning
description: Scan Express.js source files to discover all API route definitions.
allowed-tools: [Read, Grep, Glob, Bash(python3 *)]
---

# Route Scanning Skill

Discover all API route definitions in Express.js source files.

## Process

### Step 1: Run Route Scanner

Execute the scanning script:

```bash
python3 scripts/scan-routes.py <source_directory>
```

The script outputs a structured route list with method, path, file, and line number.

### Step 2: Enrich Route Data

For each discovered route, also identify:
- Middleware applied (auth, validation, etc.)
- Whether it's a standard route or chained route (`router.route()`)

### Output Format

Return a JSON-compatible route manifest:

```json
[
  {
    "method": "GET",
    "path": "/api/products",
    "file": "src/routes/products.js",
    "line": 8,
    "middleware": ["requireAuth"],
    "type": "standard"
  }
]
```

This manifest will be consumed by the next pipeline stage (doc-writing).

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (1)

Gates applied: no_behavioural_pass, no_license.