A fully loaded AI development environment with plugins, skills, specialized agents, and deep integrations — all configured for high-effort, autonomous engineering workflows.
Enhanced workflow skills: brainstorming, planning, TDD, debugging, code review, git worktrees, parallel agent dispatch, and verification before completion.
claude-plugins-officialFull-stack engineering toolkit: frontend design, browser testing, document review, git workflows, research agents, 20+ code review personas.
EveryIncLive documentation fetcher for any library, framework, or SDK. Queries current docs even when training data is outdated.
claude-plugins-officialPR review skill that orchestrates multi-persona code review with tiered agents for correctness, security, performance, and style.
claude-plugins-officialNative GitHub integration for issues, pull requests, checks, releases, and repository management via the gh CLI.
claude-plugins-officialLanguage Server Protocol support for Swift development with code intelligence, diagnostics, and completions.
claude-plugins-officialThe full skill-driven lifecycle. Each stage is backed by a dedicated skill that enforces engineering rigor.
Independent tasks are dispatched to parallel sub-agents via /dispatching-parallel-agents or /subagent-driven-development. Each agent works in isolation, then results merge back.
Feature work is isolated using /using-git-worktrees. Each worktree gets its own branch and working directory so parallel features never conflict.
Bugs trigger /systematic-debugging before any fix is proposed. Root cause analysis first, then targeted fix, then verification.
File-based memory stores user preferences, feedback, project context, and external references across sessions. Indexed via MEMORY.md.
Autonomous agents dispatched for specific tasks. Can run in parallel or foreground, each with isolated context.
Fast codebase exploration — find files, search code, answer architecture questions.
Software architect for designing implementation strategies and identifying trade-offs.
Answers questions about Claude Code features, hooks, MCP servers, and SDK usage.
Gathers official docs and best practices for any framework or library.
Archaeological git analysis — trace code evolution, understand why patterns exist.
Deep repo structure, conventions, patterns, and documentation analysis.
GitHub issue analysis — recurring themes, pain patterns, severity trends.
Researches external best practices, community conventions, and implementation guidance.
Searches past solutions to surface institutional knowledge and prevent repeated mistakes.
Always-on. Logic errors, edge cases, state management bugs, intent mismatches.
Always-on. Premature abstraction, dead code, coupling, naming clarity.
Always-on. Coverage gaps, weak assertions, brittle tests, missing edge cases.
Always-on. Audits changes against CLAUDE.md/AGENTS.md standards.
Auth, endpoints, user input, permissions — exploitable vulnerabilities.
DB queries, loops, caching, I/O — scalability and runtime issues.
Constructs failure scenarios for large or high-risk diffs.
API routes, serialization, versioning — breaking contract changes.
Migration files, schema changes, data integrity, backfill safety.
Error handling, retries, circuit breakers, timeouts, health checks.
Pattern compliance, design integrity, structural refactors.
Final pass for YAGNI violations and simplification opportunities.
OWASP compliance, input validation, hardcoded secrets, auth audits.
Algorithmic complexity, memory usage, DB queries, scalability.
Ensures agent-native parity — any user action, an agent can also take.
Design patterns, anti-patterns, naming conventions, duplication.
Migration safety, data constraints, transaction boundaries, privacy.
Cross-references schema.rb changes against included migrations.
Strict bar for type safety, clarity, and maintainability in TypeScript.
Strict bar for clarity, conventions, and maintainability in Rails.
Pythonic clarity, type hints, and maintainability.
Opinionated DHH perspective on Rails architecture and patterns.
Checks whether prior PR feedback has been addressed in the current diff.
Go/No-Go checklists, SQL verification, rollback procedures.
Reviews CLIs for AI agent readiness using severity-based rubric.
Iterative UI refinement through N screenshot-analyze-improve cycles.
Compares live UI against Figma designs for design fidelity feedback.
Detects and fixes visual differences between implementation and Figma.
Challenges premises, surfaces assumptions, stress-tests decisions.
Reviews for internal consistency, contradictions, and terminology drift.
Senior product leader perspective on scope and goal alignment.
Missing design decisions: IA, interaction states, user flows.
Plan-level security gaps: auth assumptions, data exposure, threat models.
Evaluates if proposed approaches survive reality.
Challenges unnecessary abstractions and scope creep.
Specs for flow completeness, edge cases, and requirement gaps.
Systematically reproduces and validates bug reports before fixing.
Runs linting and code quality checks on Ruby and ERB files.
Evaluates and resolves PR review threads with structured summaries.
Creates READMEs following Ankane-style template for Ruby gems.
Live documentation queries for any library, framework, or SDK. Two instances running (plugin + standalone) for redundancy.
Read, search, and manage email directly from the coding environment via OAuth authentication.
View and manage calendar events, check availability, and create meetings.
Access Notion workspaces — read pages, query databases, manage content.
Commands auto-allowed without confirmation prompt, configured in settings.local.json.
effortLevel is set to "high" globally. Every task gets maximum reasoning depth — no shortcuts, no shallow passes.
Before any action, relevant skills are checked and invoked. Skills enforce discipline: brainstorm before build, verify before ship.
Permission prompts are skipped for faster iteration. Pre-approved commands cover the common toolchain (Python, Node, git, etc.).
Draws from 3 plugin sources: Anthropic Official, EveryInc (Compound Engineering), and thedotmack (claude-mem). Community + first-party.
30+ specialized sub-agents for research, review, design, and workflow. Tasks are parallelized and isolated by default.
Persistent file-based memory indexed by MEMORY.md. Stores user context, feedback, project state, and external references across conversations.
Lifetime Claude Code activity for swchoi1994. Snapshot as of 2026-04-17.
You’ve used ~289× more tokens than Animal Farm.