analyst
01Agent
Analyze requirements, ambiguity, and hidden constraints.
Compile, verify, and run multi-agent DAGs across Pi, Codex, Claude Code, OpenCode, and Grok—with resume, replay, and incremental recomputation.
Agent
Analyze requirements, ambiguity, and hidden constraints.
Agent
Challenges planner and main-agent conclusions before risky decisions.
Agent
Author and edit documentation FILES on disk (README, guides, changelogs, docs).
Agent
Full-capability code executor for complex multi-file changes.
Agent
Fast executor for scanning, command runs, summaries, and low-risk small edits.
Agent
UI-focused executor for frontend component, layout, and styling changes.
Agent
Implement planned code changes.
Agent
Makes final decisions when multiple plans, critiques, or reviews conflict.
Agent
Reviews and challenges implementation plans before execution on complex tasks.
Agent
Creates concrete implementation plans, risk analysis, and acceptance criteria without editing files.
Agent
Continue from a compact handoff — finds latest SESSIONSTATE.md and HANDOFF.md in .agent/, then acts on Next Actions.
Agent
Reviews code, plans, architecture risk, and test gaps without editing files.
Agent
Engineering risk review for backend, data, and infrastructure changes.
Agent
Fast codebase recon that returns compressed context for handoff to other agents.
Agent
Review changes for security vulnerabilities and trust-boundary issues.
Agent
Design and implement test strategy for a change.
Agent
Runs validation commands, reproduces failures, and checks logs without editing files.
Agent
Analyzes Figma design metadata, tokens, and specs from text-based context.