Features
Deep reasoning for multi-step coding tasks
Multi-file context awareness across codebase
Dynamic Workflows for adaptive agentic processes
Custom skills and subagents for specialized tasks
Plugin and MCP integration for extended capabilities
Claude.md configuration file for project-specific settings
Undocumented advanced configuration options from source
Artifacts for live web pages with auto-update and version history
Code generation, explanation, debugging, and refactoring assistance
Extended Thinking for step-by-step reasoning (note: fabricated citations reported)
Git-based interaction for codebase context
Real-time conversation and code changes across files
Parallel agent execution on desktop (redesigned version)
Steganographic marking of requests for unauthorized use detection
Community tool Recall for local project memory
Live knowledge graph from code, commits, issues, and docs
Feasibility analysis: flags buildable vs risky items
Technical design document generation grounded in service topology
Impact assessment maps services, APIs, and dependencies across repos
Auto-scoping epics into Jira/Linear stories with effort estimates
One-shot production code generation grounded in service patterns
AI code reviews with cross-repo impact analysis
Production issue triage via MCP
Conversational learning from Slack and Jira
Accelerated onboarding via system-level Q&A in coding agents
Create Jira tickets and merge requests from Slack
MCP server for integration with Cursor, Claude Code, Codex
On-prem or cloud deployment
No code storage or model training
