Spec-driven multi-agent orchestration plugin for Claude Code — 13 agents, 35 skills, per-phase model tiers, opt-in lifecycle hooks, and optional cross-device semantic memory.
Agent
Requirements analyst. MUST BE USED for ambiguous requests, requirements gathering, scope assessment, feasibility checks, and proposal writing. NOT for small, clearly-scoped changes (those go directly to developer). PROACTIVELY interprets user intent and produces proposal.md specs.
Agent
Technical architect. MUST BE USED for system design, API design, implementation planning, multi-file refactoring, and agent orchestration. Receives proposal.md from analyst and produces design.md + tasks.md.
Agent
Analyzes tasks and decomposes them into a sequence of agent steps for execution.
Agent
Bug investigation specialist. MUST BE USED for bug reports, unexpected behavior, error diagnosis. PROACTIVELY performs systematic root cause analysis using progressive debugging techniques.
Agent
Expert software engineer. Use proactively to implement features, fix bugs, write tests, style UI, and make code changes. MUST BE USED for all development tasks. Direct target for small, clearly-scoped changes — no analyst/architect needed first.
Agent
Infrastructure specialist. MUST BE USED for CI/CD, Docker, deployment, infrastructure. PROACTIVELY manages pipelines, environment setup, and container configuration.
Agent
Git operations specialist. MUST BE USED for branch management, conflict resolution, git history analysis, worktree recovery, commit, merge, push. Owns ALL git operations — other agents do NOT commit.
Agent
MCP server specialist. MUST BE USED to design, build, and test MCP servers — stdio vs http transports, tool schema design, env-based secrets, and the Vault-launcher pattern. PROACTIVELY keeps secrets out of source and tool schemas tight.
Agent
Performance specialist. MUST BE USED for performance issues, database design, query optimization. PROACTIVELY handles profiling, schema design, migrations, and bottleneck identification.
Agent
Prompt & guardrail engineering specialist. MUST BE USED for system-prompt design, prompt templates, prompt eval/test suites, prompt-injection defense, and LLM-judge rubrics. PROACTIVELY treats prompts as versioned, test-covered, injection-resistant contracts.
Agent
Documentation researcher. MUST BE USED for new API integration, library questions, best practices. PROACTIVELY gathers version-specific documentation and produces ResearchPacks with citations.
Agent
Senior code reviewer, security specialist, and quality assurance expert. Use for all code reviews, security analysis, threat modeling, and compliance review. MUST BE USED for all reviews.
Agent
Documentation owner. MUST BE USED for README, CHANGELOG, docs/ updates. PROACTIVELY manages all markdown files as sole authority for documentation.