Stats
Actions
Tags
From claude-dev-team
Multi-agent development workflow using Agent Teams. Supports four modes: plan (architect + PM debate → plan.md), dev (developer + tester + reviewer iterate → code), full (plan → approval gate → dev), and auto (plan → dev, no gate). Use when tasks benefit from collaborative agent roles with peer messaging.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-dev-team:claude-dev-teamThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Multi-agent development workflow with four modes. Pick one based on the user's needs:
Multi-agent development workflow with four modes. Pick one based on the user's needs:
| Mode | When to use |
|---|---|
| plan | Need architecture/design before coding |
| dev | Have an approved plan, ready to implement |
| full | End-to-end with user approval gate between plan and dev |
| auto | End-to-end without approval gate |
Before executing any mode, read references/WORKFLOW.md for detailed step-by-step instructions, spawn prompts, and output templates.
Plan Phase (plan/full/auto) Dev Phase (dev/full/auto)
Lead (You) Lead (You)
├── architect [teammate] ├── developer [teammate]
├── prod-mgr [teammate] ├── tester [teammate]
└── researcher [subagent] ├── reviewer [teammate]
└── researcher [subagent]
│ │
└──── plan.md (handoff) ─────────┘
Teammates message each other directly (Architect↔PM, Dev↔Tester↔Reviewer). Researcher is a subagent — Lead relays results.
Research specialist for doc lookups. Queries Context7 for library docs, searches web for best practices, returns structured findings with code examples. Bundled as agents/researcher.md in this plugin — Context7 MCP is auto-configured via .mcp.json.
Designs architecture: components, interfaces, file changes, data flow, testing strategy. Debates tradeoffs with PM. Messages design to lead and PM.
Validates architecture against requirements. Challenges design with concerns. Produces verdict: APPROVED or NEEDS_REVISION with specifics.
Implements tasks from plan. No stubs, no TODOs. Matches existing patterns. Iterates with tester on failures, reviewer on issues.
Writes and runs tests matching existing patterns. Messages developer with specific failures + root cause. Max 3 fix cycles, then escalates to lead.
Reviews changed files for completeness, correctness, security, quality, plan adherence. Validates review with /council (quick quality for routine, review security or review architecture for critical concerns). Scans for stubs. Messages developer with file:line + fix suggestions. Max 3 cycles.
depends_on; parallel within waves, sequential betweennpx claudepluginhub chalet-labs/chalet-agent-dev-teamSets up multi-agent teams for complex projects with file-based planning, per-agent directories, and teammate spawning. Triggers on team/swarm/start-project requests.
Guides coordination of parallel agent teams (Implementer, Reviewer, Architect) for complex plans, cross-cutting concerns, and communicating work streams.
Analyzes complex tasks, scouts codebase, dynamically designs and assembles expert agent teams via TeamCreate API, executes with validation and user confirmation.