architect
01Agent
Use this agent for design decisions, architectural analysis, solution proposals, and structural recommendations. Read-only — produces designs, not code.
Dream Team is a Claude Code plugin offering structured planning capabilities that generate specification files. It features a universal build skill that interprets these specifications and executes them using role-based agents with tailored strategies.
Agent
Use this agent for design decisions, architectural analysis, solution proposals, and structural recommendations. Read-only — produces designs, not code.
Agent
Use this agent when code needs to be written, files created, or features implemented. Executes ONE task at a time with full read/write access. Uses TDD. Follows specs exactly.
Agent
Use this agent for systematic debugging. Reproduces issues, forms hypotheses, investigates root causes, applies targeted fixes, and verifies resolution. Interactive and methodical — understand it before fixing it.
Agent
Use this agent after all code is written to produce and update project documentation. Reviews changes against the spec's Documentation Requirements section and writes README updates, changelog entries, API docs, and inline comments for complex logic. Read-write — modifies documentation files only.
Agent
Use this agent for branch integration in delegated mode. Merges builder worktree branches back into the feature branch with tiered conflict resolution. Dispatched by the orchestrator after builder completion and review approval.
Agent
Use this agent for codebase exploration, documentation research, pattern investigation, and gathering context. Read-only — cannot write or edit files.
Agent
Use this agent for qualitative code review against specs and coding standards. Categorizes issues by severity. Read-only — cannot modify files.
Agent
Use this agent for fast, cheap pre-build reconnaissance. Scans file structures, identifies patterns and conventions, reports gotchas. Read-only — haiku model for cost efficiency. Dispatched by the orchestrator before builders on complex tasks.
Agent
Use this agent for proactive security auditing of code changes. Works through a structured 7-category checklist on every review. Read-only — cannot modify files.
Agent
Use this agent for independent adversarial testing, integration tests spanning multiple components, and security/boundary testing. Writes test files only — cannot modify source code. Complements builder TDD by testing from the spec (not the implementation) and targeting edge cases builders miss.
Agent
Use this agent for final mechanical verification. Runs validation commands, checks acceptance criteria, produces pass/fail report. Read-only.