Features
5-phase workflow: Investigate, Design, Implement, Verify, Ship
15 skills with rationalizations tables and evidence requirements
8 specialist agents (Planner, Architect, Experience-Reviewer, etc.)
5 output styles: Brainstorm, Deep Research, Implementation, Review, Token Efficient
Pre-completion verification gates requiring pasted evidence
Root-cause investigation (4-phase, no fix without written hypothesis)
Falsifiable plans with file paths and exact test commands
Rationalizations tables naming and rebutting skip-excuses
One-time scaffolding wizard for project configuration
Incremental shipping with vertical slices behind feature flags
Evidence-driven debugging with active paper trail
Atomic releases with reviewable PRs and verification evidence
Skills activate automatically by user intent
Install via Claude Code marketplace
MCP servers for library docs, persistent memory, browser automation, reasoning
Autonomous vulnerability scanning and PR generation
PR review for quality, security, and best practices
Legacy COBOL to Java migration with testing
Incident triage and root cause analysis
Agent Canvas: manage multiple agents in one workspace
Cloud agents run even when your machine is off
Schedule recurring tasks via cron or event triggers
Trigger workflows from GitHub, Slack, PagerDuty
Model-agnostic: supports Claude Code, Codex, Gemini CLI, MiniMax M2.7
Isolated sandbox execution on VM or cloud
Fine-grained access control and budget guardrails
Audit trails for enterprise compliance
Self-hosted deployment in your VPC
Open-source SDK for custom agent development
In-chat model switching with saved LLM profiles
