claude-auto-dev

Show token / tool usage stats from the local telemetry log. Use when you want to know "which tools am I burning context on", "which skills are expensive", or "was yesterday's session mostly Read/Grep or actually productive".

Parallel quality audit with 7 specialized agents (Opus). Finds bugs, violations, and quality issues. Use audit for fixes, brainstorm for features.

Manage environment variables with Doppler — auto-install CLI, login, link projects, wrap commands with `doppler run`. Replaces scattered .env files with a hub/spoke architecture.

Scaffolds new projects or onboards existing ones. Detects stack, creates monorepo/single-app, configures strict tooling. Use for greenfield or first-time setup.

Archives completed stories from prd.json to reduce token usage.

Autonomous task execution with testing and security. Works through all tasks without stopping.

Removes temporary screenshots, old backups, stale handoffs, and auto-active flags. Use when project has accumulated temp files.

Manages environment variables and credentials securely. Use when configuring secrets or .env files.

Shows sprint progress and task status. Use 'progress' (not 'status' - that's a built-in).

Updates claude-auto-dev to latest version. Syncs repo with ~/.claude.

Backs up auto-memory files to a private GitHub repo. One-command setup, committed daily via Task Scheduler (or on-demand). Restore is a single clone.

Search persistent project memory across sessions — decisions, bugs, features, discoveries

Feature ideation, dead code cleanup, and product thinking. Proposes new features and architecture improvements — not bugs or violations (use audit for those).

prd.json schema and task system - auto-loaded when prd.json exists

Live site QA via agent-browser (token-efficient) and Playwright (login flows). Scans pages, catches visual/functional issues, compares with baselines. Use when testing a live site or after deploying.

Debugs and fixes issues systematically. Use when something is broken, throwing errors, or behaving unexpectedly.

Dependency updates, major version upgrades, and breaking change resolution. Use when updating packages or handling deprecations.

Code quality check with adaptive effort scaling. Includes security scanning.

Standardized git commit, push, and PR creation workflow.

Deploy workflow for Vercel, Supabase, and CI/CD pipelines. Use for deployment and CI/CD setup.

Creates distinctive UI with preserved structure. Avoids generic AI aesthetics. Use when designing or refining user interfaces.

Pre-deploy security audit with vulnerability pattern scanning. Auto-loaded with review, audit, ship.

Pre-deploy checklist with review, security, and test verification. Use when ready to deploy.

Type safety, design tokens, UI states, React/Next.js patterns from production.

Supabase CLI, Postgres performance, and schema patterns. Use for database operations, queries, RLS, and migrations.

Runs unit and browser tests on latest changes. Use after implementing features or fixing bugs.

Comprehensive PR review using specialized agents. Use before creating or merging pull requests.

Browser automation CLI for AI agents. 5-6x more token-efficient than Playwright MCP. Use for browser testing and web automation.

Convergence loop — brainstorm, fix, re-scan until the codebase is clean. Combines brainstorm→apply→auto in one command.

Creates or advances sprints in prd.json. Use when starting new work cycles or closing completed sprints.

SEO audit and structured data patterns - meta tags, Open Graph, JSON-LD schema, Core Web Vitals. Use for marketing sites and e-commerce.

Stripe integration patterns - API keys, webhooks, checkout, subscriptions. Loads when working with payments.

Observability patterns for production - logging, error tracking, analytics. Use when setting up monitoring.

Best practices for Remotion - video creation in React. Use when working with video compositions, animations, or subtitles.

Accessibility audit and patterns - WCAG 2.1 AA compliance for React apps.

Web performance audit - Core Web Vitals, bundle analysis, Lighthouse patterns.

Code refactoring patterns - extract, split, restructure without changing behavior.