{
  "markdown": "# claude-beta-tester\n\n> A Claude Code plugin that runs AI-powered browser testing against any URL using personality-driven agents — speedrunners, chaos gremlins, skeptical executives, and more.\n\n## Plugin Installation (Claude Plugin Directory)\n\nOnce listed in the Claude plugin directory:\n```bash\nclaude plugin install claude-beta-tester@claude-community\n```\n\nCommands will be available as `/claude-beta-tester:beta-test`.\n\n## Manual Install\n\n```bash\n# Clone into your Claude config directory\ngit clone https://github.com/rjspence3/claude-beta-tester ~/.claude/plugins/claude-beta-tester\n\n# Copy command\ncp ~/.claude/plugins/claude-beta-tester/.claude/commands/beta-test.md ~/.claude/commands/\n```\n\nCommand is available immediately in Claude Code as `/beta-test`.\n\n## What it does\n\n`/beta-test` runs the `ai-beta-test` CLI against a target URL with one or more personality-driven agents. Each agent has a different mindset and surfaces different categories of issues.\n\n### Available personalities\n\n| Name | Mindset | What it surfaces |\n|------|---------|-----------------|\n| `speedrunner` | *\"I don't have time for this.\"* | Missing loading states, unclear primary actions, broken fast-paths |\n| `chaos_gremlin` | *\"What happens if I do this?\"* | Input validation gaps, error handling issues, state corruption |\n| `skeptical_exec` | *\"I don't trust this tool yet.\"* | Cognitive load, trust breaks, unexpected transitions |\n| `methodical_newcomer` | *\"I am new here.\"* | Missing guidance, confusing labels, dead ends |\n| `overloaded_manager` | *\"I have 30 seconds.\"* | Poor hierarchy, information overload, slow landing |\n| `calm_operator` | *\"Slow and steady.\"* | Missing feedback, inconsistency, unclear state |\n| `adhd_founder` | *\"Oh look, a shiny feature!\"* | Poor resumption, brittle state, punitive flows |\n| `privacy_paranoid` | *\"Why do you need to know that?\"* | Trust breaks, missing provenance, dark patterns |\n| `feature_explorer` | *\"Show me everything.\"* | Undiscoverable features, navigation gaps |\n| `interactive_explorer` | *\"I'll use every single one.\"* | Incomplete flows, missing feedback |\n| `technical_exploit` | *\"I don't play by the rules.\"* | Security hints, exposed storage, validation bypasses |\n| `hybrid_auditor` | *\"I read the blueprints.\"* | Security risks, logic errors, API failures |\n| `agentic_interface_tester` | *\"AI interface UX researcher.\"* | Mode selection errors, decision transparency |\n\n**Default set:** `speedrunner`, `chaos_gremlin`, `skeptical_exec`\n\n## Usage\n\n```\n/beta-test\n```\n\nClaude will ask for:\n1. Target URL\n2. Goal (one sentence — e.g., \"Complete the onboarding flow\")\n3. Personalities to run (or say `default`)\n\nOr provide them directly:\n\n```\n/beta-test https://myapp.com\n```\n\n## Requirements\n\nRequires `ai-beta-test` CLI and Node.js 18+:\n\n```bash\n# From the repo (development)\npip install -e ~/Development/ai-beta-tester\n\n# Or once published\npip install ai-beta-tester\n\n# Node.js (required for Playwright MCP server)\nbrew install node\n```\n\n---\n\nBuilt by [Rob Spence](https://nomouthlabs.com). MIT License.\n",
  "bytes": 3064,
  "sha": "5bb9a5072e0d585f5b95e78862b1a56d09b6c775ec9ae740c0e1fc490dd8f9ea",
  "repo_slug": "rjspence3/claude-beta-tester",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_rjspence3_claude_beta_tester_agentic_bet_a94acf53/readme"
}