Plugin Claude Code
George's Claude Code plugins.
Plugin Claude Code
George's Claude Code plugins.
Plugin Claude Code
Fully autonomous overnight coding agent. Give it a mission, walk away for hours, come back to a better codebase. Supports mission-driven development, codebase improvement, plan execution, and deep research modes. Fresh-context loop pattern with file-based memory for unlimited runtime.
Agent
Manages safe production deployments via Vercel canary releases. Deploys to preview, monitors for errors, then promotes or reports rollback.
Agent
Independent post-milestone code quality evaluator. Reviews all changes for quality, security, and test coverage after a milestone or phase completes. Read-only — never modifies code.
Agent
Code implementation agent for autopilot. Writes, edits, and tests code changes. Follows existing patterns, handles edge cases, and self-reviews before reporting completion.
Agent
Codebase health analysis agent for autopilot improve mode. Scans for test gaps, lint issues, performance problems, security risks, and code quality issues. Outputs a prioritized improvement plan.
Agent
Generates legal documents (Terms of Service, Privacy Policy, Cookie Policy, AUP) from app metadata. Outputs ready-to-customize templates.
Agent
Autonomous content marketing generator. Creates blog posts, social media content, pSEO pages, and email campaigns from product data.
Agent
Task decomposition agent for autopilot. Analyzes a high-level mission and breaks it into concrete, atomic tasks. Prioritizes by impact and dependency order.
Agent
Autonomous PostHog analytics analyzer. Reads user metrics, identifies patterns, and generates prioritized improvement recommendations.
Agent
Deep research agent for autopilot. Investigates codebases, searches the web, reads documentation, and produces structured findings. Use when a task requires understanding before implementation.
Agent
Market research and product strategy agent. Analyzes competitors, defines MVP features, and recommends pricing and tech stack for new SaaS products.
Agent
Independent security review agent. Scans code changes for vulnerabilities using OWASP Top 10 and SaaS-specific checks. Read-only — never modifies code.
Agent
Autonomous Sentry issue scanner and fixer. Reads production errors, identifies root causes, implements fixes, and creates commits.
Agent
Milestone strategist for evolve mode. Conducts external market research (competitors, trends, innovations), analyzes codebase holistically, and generates prioritized product-level milestones. Re-evaluates after each milestone completes.
Agent
Independent verification agent for autopilot. Reviews code changes with fresh eyes, runs tests, checks for regressions. Never modifies code directly — only reports findings.
Command
Verify service credentials and auth state for autonomous operations.
Command
Generate a comprehensive report of what autopilot accomplished.
Command
Resume a stopped autopilot session from its handoff state.
Command
Check autonomous loop progress, completed tasks, and current state.
Command
Gracefully stop the autonomous loop.
Command
Start autonomous coding loop. Modes: mission (default), improve, execute, research, evolve, build-saas, marketing.
Command
Show cost tracking report for autopilot runs.
Command
Analyze PostHog metrics and generate improvement recommendations.