fengjunhui31/building-autonomous-team
Plugin Claude Code
Mission-driven autonomous team — 2 persistent agents + Team Lead-managed members, SendMessage communication, GitHub-only state, event-driven, two-round perspective discussions.
fengjunhui31/building-autonomous-team
Instructions file
Claude Code instructions for fengjunhui31/building-autonomous-team, covering claude.md, project overview, repository structure, architecture and dynamic agents.
fengjunhui31/building-autonomous-team
Plugin Claude Code
Mission-driven autonomous team — 2 persistent agents + Team Lead-managed members, SendMessage communication, GitHub-only state, event-driven, two-round perspective discussions.
fengjunhui31/building-autonomous-team
Agent
Acceptance Tester — Validate implementation against Spec (spawn on demand).
fengjunhui31/building-autonomous-team
Agent
Code Reviewer — Code quality inspection (spawn on demand).
fengjunhui31/building-autonomous-team
Agent
Cost Analyst — Cost/resource perspective, participates in two-round discussions (spawn on demand).
fengjunhui31/building-autonomous-team
Agent
Executor — Implement code per Spec in isolated worktree, create PR (spawn on demand).
fengjunhui31/building-autonomous-team
Agent
Impl Coordinator — dynamic per-Discussion agent that coordinates Executor, Reviewers, and merge after Spec is ready.
fengjunhui31/building-autonomous-team
Agent
Mission Analyst — Analyze codebase vs mission gap, propose next topics (spawn on demand).
fengjunhui31/building-autonomous-team
Agent
Performance Expert — Performance perspective, participates in two-round discussions (spawn on demand).
fengjunhui31/building-autonomous-team
Agent
Product Owner — User value perspective, participates in two-round discussions (spawn on demand).
fengjunhui31/building-autonomous-team
Agent
Project Manager — persistent agent that drives Discussion queue, organizes consensus panels, writes Spec, and advances topics.
fengjunhui31/building-autonomous-team
Agent
Security Expert — Security perspective, participates in two-round discussions (spawn on demand).
fengjunhui31/building-autonomous-team
Agent
Security Reviewer — Security audit of implementation (spawn on demand).
fengjunhui31/building-autonomous-team
Agent
Technical Architect — Technical perspective and solution design, participates in two-round discussions (spawn on demand).
fengjunhui31/building-autonomous-team
Command
Set up, operate, or update an autonomous team — auto-detects mode. Optional language argument (e.g. /building-autonomous-team 中文).
fengjunhui31/building-autonomous-team
Hook
Runs before the agent uses a tool for Agent tool calls, executing check-executor-worktree.sh. From fengjunhui31/building-autonomous-team.
fengjunhui31/building-autonomous-team
Skill Claude CodeCodex
Use when creating a new autonomous team for a project — sets up 2 persistent agents + dynamic spawn architecture with GitHub-native state management.
fengjunhui31/building-autonomous-team
Skill Claude CodeCodex
Use when operating an existing autonomous team — pre-flight git checks, recover Project Manager, start heartbeat loop.
fengjunhui31/building-autonomous-team
Skill Claude CodeCodex
Use when upgrading an existing autonomous team to the latest plugin version — updates agent definitions, workflow, preserves customizations.