automation

agentscan: Automate Pattern Detection

Detect automation patterns with agentscan, a tool, built with TypeScript.
intermediateโฑ 30 minutes๐Ÿ’ต Free + LLM API costs
87 stars15 forksTypeScriptGuide quality 8/10Updated 9/1/2026100% free ยท open source
What it is

Use agentscan to detect automation patterns in code, like tools and tools' dependencies.

Real use case example

"A founder, Maria, sets up agentscan to scan her GitHub repository for automations. She creates a new repository, and agentscan flags a potential automated web scraper, which Maria then investigates and corrects. With this, she ensures her new repository doesn't accidentally scrape sensitive data."

Best insideClaude DesktopClaude CodeSelf-hosted
When to use it
  • โ€ขWhen you suspect a repository is being automated and want to verify
  • โ€ขTo identify potential security risks from automated commits
  • โ€ขTo analyze commit patterns for insights on repository maintenance
Ready-to-paste prompt
npx ts-node src/analyze.ts https://github.com/MatteoGabriele/agentscan
Heads up: Ensure you have Node.js and TypeScript installed on your system, as agentscan is built with TypeScript and requires a compatible runtime environment to execute
Saves to your device
Use with Claude
New

Skip the builder โ€” one click puts this in Claude, Cursor, Antigravity and more.

๐Ÿ› ๏ธ Technical setup

Expect 20โ€“40 minutes in a terminal โ€” or let your AI agent drive it.

Try it instantly โ€” no install
Claude Code
mkdir -p ~/.claude/skills/agentscan && curl -fsSL https://workflowstacks.com/api/skills/agentscan/claude-skill -o ~/.claude/skills/agentscan/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go โ€” no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How agentscan: Automate Pattern Detection works
Codeflow
Free to inspect

Agentscan: Automate Pattern Detection is a large project (~15k lines across 172 code files, plus 7 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size
Large codebase
~15k lines ยท 172 code files ยท ~2 h to skim
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js
No API keys detected
Where to start reading
  1. 1
    README.md
    Start here โ€” what it does and how to install it
  2. 2
    package.json
    Dependencies and the commands it exposes
  3. 3
    app/pages/app.vue
    Inside app/ โ€” the main logic begins here
What's in each folder
app/Core code โ€” the actual logic107 files
server/Backend / API25 files
shared/Folder32 files
scripts/Helper scripts10 files
data/Data files2 files
mock-data/Folder1 files
.github/CI / automation (GitHub Actions)11 files
public/Images & static assets8 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
MatteoGabriele
Language
TypeScript
Category
automation
Published
2/14/2026

Are you the creator of this tool? Claim your listing โ†’ and earn 85% of every sale.