By karbassi
A subagent for browser automation and web research using chrome-devtools
A collection of Claude Code plugins by Ali Karbassi.
First, add the marketplace:
claude plugin marketplace add karbassi/claude-plugins
Then install plugins with your preferred scope:
claude plugin install github@karbassi-claude-plugins --scope <scope>
| Scope | Flag | Description |
|---|---|---|
| user | --scope user | Installed globally for your user account. Available in all projects. This is the default if no scope is specified. |
| project | --scope project | Installed for the current project. Configuration stored in project settings and can be shared via version control. |
| local | --scope local | Installed for the current working directory only. Most restrictive scope. |
# Install globally (available everywhere)
claude plugin install github@karbassi-claude-plugins --scope user
# Install for this project (recommended for team projects)
claude plugin install github@karbassi-claude-plugins --scope project
# Install for this directory only
claude plugin install github@karbassi-claude-plugins --scope local
user - Personal plugins you want everywhere (default)project - Team projects where plugins should be shared via version controllocal - Testing plugins or directory-specific workflows| Plugin | Description |
|---|---|
| changelog-manager | Maintain CHANGELOG.md following Keep a Changelog format |
| note-taker | Background note-taker that captures decisions, action items, blockers, and key findings |
| git-agent | Subagent that handles git operations (commit, stage, etc.) |
| docs-update | Subagent that updates project documentation files |
| todo-update | Subagent that keeps TODO.md current with task status |
| browser-research | Subagent for browser automation and web research |
| github | Unified GitHub agent for issues, PRs, and code reviews |
| youtube-transcript | Fetch and present transcripts from YouTube videos |
claude-plugins/
├── .claude-plugin/
│ └── marketplace.json # Plugin registry
├── plugins/
│ ├── changelog-manager/ # Changelog maintenance
│ ├── note-taker/ # Background note-taking
│ ├── git-agent/ # Git operations
│ ├── docs-update/ # Documentation updates
│ ├── todo-update/ # Task tracking
│ ├── browser-research/ # Browser automation
│ ├── github/ # GitHub issues & PR reviews
│ └── youtube-transcript/ # YouTube video transcripts
└── README.md
MIT
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Unified GitHub agent for issues, PRs, and code reviews
A subagent that handles all git operations (commit, stage, etc.)
A subagent that keeps TODO.md current with task status
A subagent that updates project documentation files
Fetch and present transcripts from YouTube videos using yt-dlp
npx claudepluginhub karbassi/claude-plugins --plugin browser-researchBrowser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows.
Browser automation skill for Claude Code using Stagehand. Automate web interactions, extract data, and navigate websites using natural language.
Chrome DevTools Protocol (CDP) browser automation, web scraping, and crawling with React compatibility
Direct browser control via CDP. Drives the user's real Chrome (or a Browser Use cloud browser) with coordinate clicks, screenshots, and Python helpers — no selector hunting. Requires the one-time `browser-harness` CLI install (see the skill's references/install.md).
AI-powered browser automation -- lets Claude control real web browsers to navigate, click, type, extract content, and automate workflows
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script. Originally from OpenAI's curated skills catalog.