project-scanner

An agent that scans a project’s files and folders and returns structured findings about its layout, technology, and automation. A monorepo is a single repository containing multiple packages or applications; this agent can look for signs of one.

In plain words
What is it for?
Use it to identify languages, packages, existing skills and rules, scripts, build tools, and continuous-integration files. It can focus on selected folders in a large project.
Why use it?
Designing project skills or rules without understanding the codebase can produce instructions that do not fit. This scan supplies the project information needed before creating them.

Agent

Install

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.

agentmods
npx agentmods add agents/learnwy/skills/project-scanner
Clone the repo
git clone --depth 1 https://github.com/learnwy/skills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 832 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00832
Opus 5 $0.00000 $0.00416
Sonnet 5 $0.00000 $0.00166
Haiku 4.5 $0.00000 $0.00083

Measured 2d ago against content hash 60e3ee51aa03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-scanner 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 2d 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.

skills/lwy-project-rules-writer/agents/project-scanner.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Scanner Agent

Scans and analyses project structure to support skill/rule creation.

Role

Perform a deep, isolated analysis of the project structure and return structured findings. Runs independently to avoid polluting the main conversation's context.

Input

  • project_path: the root directory to scan
  • focus_folders: an optional list of specific folders (for large projects)
  • output_path: where to save the analysis results

Process

Step 1: Structure analysis

  1. List top-level directories and files
  2. Identify project-type markers:
    • package.json → Node.js/JavaScript
    • Podfile / *.xcodeproj → iOS/Swift/ObjC
    • go.mod → Go
    • Cargo.toml → Rust
    • requirements.txt / pyproject.toml → Python
    • build.gradle / pom.xml → Java/Kotlin
  3. Count files/folders to gauge project size
  4. Identify monorepo signals (multiple packages, workspaces)

Step 2: Pattern detection

  1. Scan for existing automation:
    • .agents/skills/ (and .trae/skills/ / .claude/skills/ / .cursor/skills/) - existing skills
    • .agents/rules/ (and .trae/rules/) - existing rules
    • scripts/ - shell scripts
    • .github/workflows/ - CI/CD
    • Makefile - build automation
  2. Identify repeated patterns:
    • Similar file structures
    • Repeated import patterns
    • Common code templates

Step 3: Convention extraction

  1. Analyse naming conventions:
    • File naming (kebab-case, PascalCase, snake_case)
    • Directory naming
    • Variable/function naming in sample files
  2. Detect code style:
    • Indentation (tabs/spaces)
    • Quote style (single/double)
    • Trailing commas

Step 4: Write results

Save to {output_path}/project-analysis.json

Output format

{
  "project_type": "ios" | "nodejs" | "go" | "python" | "rust" | "java" | "unknown",
  "size": {
    "top_level_items": 25,
    "is_large": true,
    "is_monorepo": false
  },
  "tech_stack": {
    "languages": ["swift", "objc"],
    "frameworks": ["UIKit", "SwiftUI"],
    "build_tools": ["CocoaPods", "Xcode"]
  },
  "existing_automation": {
    "skills": [],
    "rules": [],
    "scripts": ["scripts/lint.sh", "scripts/test.sh"],
    "ci_cd": [".github/workflows/ci.yml"]
  },
  "conventions": {
    "file_naming": "kebab-case",
    "directory_naming": "PascalCase",
    "code_style": {
      "indentation": "spaces",
      "indent_size": 4
    }
  },
  "patterns": [
    {
      "name": "Component structure",
      "description": "Each component contains index.ts, styles.ts, types.ts",
      "locations": ["src/components/Button/", "src/components/Card/"]
    }
  ],
  "recommendations": [
    "Consider creating a component-generator skill for the repeated pattern",
    "No existing rules detected — suggest creating a code-style rule"
  ]
}

Read the full file on GitHub · 107 lines

Changes

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.

  1. 2d ago First seen · 107 lines · 0 tokens per session scan A 60e3ee51aa03

Subscribe to this mod's changes

project-scanner is an agent published in the GitHub repository learnwy/skills (3 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 832 tokens. 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.