vc:team
The vc:team skill orchestrates multiple independent Claude Code sessions running in parallel to collaborate on research, implementation, review, and debug workflows. Use it when you need independent teammates working simultaneously on shared tasks with separate context windows, but only in CLI terminal mode with Agent Teams explicitly enabled via `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` and Opus 4.6 models available.
git clone --depth 1 https://github.com/withkynam/vibecode-pro-max-kit /tmp/vc-team && cp -r /tmp/vc-team/.claude/skills/vc-team ~/.claude/skills/vc-teamSKILL.md
# Agent Teams - Parallel Orchestration Utility
Coordinate multiple independent Claude Code sessions. Each teammate has own context window, loads project context (CLAUDE.md, skills, agents), communicates via shared task list and messaging.
**Requires:** Agent Teams enabled. Set `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` in settings.json env.
**Requires:** CLI terminal — `TaskCreate`/`TaskUpdate`/`TaskGet`/`TaskList` and `TeamCreate`/`TeamDelete` are **disabled in VSCode extension** (`isTTY` check). Agent Teams CANNOT run in VSCode.
**Model requirement:** All teammates must run Opus 4.6 (Agent Teams constraint).
## Usage
```
/vc:team <template> <context> [flags]
```
**Templates:** `research`, `execute`, `review`, `debug`
**Flags:**
- `--devs N` | `--researchers N` | `--reviewers N` | `--debuggers N` -- team size
- `--plan-approval` / `--no-plan-approval` -- plan gate (default: on for execute)
- `--delegate` -- lead only coordinates, never touches code
- `--worktree` -- use git worktrees for implementation isolation (default: on for execute)
## Execution Protocol
**Pre-flight (MANDATORY -- merged into step 2 of every template):**
1. Step 2 of every template calls `TeamCreate(team_name: "...", ...)`. Do NOT check whether the tool exists first -- just call it.
2. If the call SUCCEEDS: continue with the template.
3. If the call returns an ERROR or is unrecognized: **STOP. Tell user:** "Agent Teams requires `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` in settings.json. Team mode is not available."
4. Do NOT fall back to subagents. `/vc:team` MUST use Agent Teams or abort.
5. Ensure `TeamCreate` was called before spawning teammates -- team association happens via session context.
When activated, first confirm team creation if the user has not already explicitly approved using agent teams for this task.
Do not use this skill to bypass the repo's normal human approval gates.
Execute the tool calls in order only after team usage is approved. Report progress after each major step.
### --delegate Mode
When `--delegate` flag is passed:
- Lead enters delegate mode (`Shift+Tab` after TeamCreate)
- Lead ONLY: spawns teammates, manages tasks, sends messages, synthesizes reports
- Lead NEVER: edits files, runs tests, executes git commands directly
- For execute Step 7 MERGE: spawn a dedicated merge teammate instead of lead doing it
- For all templates: lead coordinates and reports, delegates ALL implementation work
---
## Tool Reference (Quick)
### Agent Tool (spawn teammates)
```
Agent(
subagent_type: "research-agent" | "execute-agent" | "code-reviewer" | "debugger" | "tester" | ...,
description: "short task summary",
prompt: "full instructions + CK Context Block",
model: "opus", # Required for Agent Teams teammates
run_in_background: true, # Non-blocking spawn
isolation: "worktree" # Git worktree isolation (execute devs)
)
```
**Note:** `Task` was renamed to `Agent` in v2.1.63. Both names work; prefer `Agent` for new code.
### Team Management Tools
| Tool | Purpose | Params |
|------|---------|--------|
| `TeamCreate` | Create team + task list | `team_name`, `description` |
| `TeamDelete` | Remove team resources | *none* -- just call it |
| `TaskCreate` | Create work item | `subject`, `description`, `priority`, `addBlockedBy`, `addBlocks` |
| `TaskUpdate` | Claim/complete task | `taskId`, `status`, `owner`, `metadata` |
| `TaskGet` | Full task details | `taskId` |
| `TaskList` | All tasks (minimal fields) | *none* |
| `SendMessage` | Inter-agent messaging | `type`, `to`/`recipient`, `message` |
### SendMessage Types
| Type | Purpose |
|------|---------|
| `message` | DM to one teammate (requires `recipient`) |
| `broadcast` | Send to ALL teammates (use sparingly) |
| `shutdown_request` | Ask teammate to gracefully exit |
| `shutdown_response` | Teammate approves/rejects shutdown (requires `request_id`) |
| `plan_approval_response` | Lead approves/rejects teammate plan (requires `request_id`) |
---
## CK Context Block
Every teammate spawn prompt MUST include this context at the end:
```
CK Context:
- Work dir: {CK_PROJECT_ROOT or CWD}
- Feature: {CK_FEATURE or "none"}
- Reports: {CK_REPORTS_PATH or "process/general-plans/reports/"}
- Plans: {CK_PLANS_PATH or "process/general-plans/active/"}
- Branch: {CK_GIT_BRANCH or current branch}
- Naming: {CK_NAME_PATTERN or "YYMMDD-HHMM"}
- Active plan: {CK_ACTIVE_PLAN or "none"}
- Commits: conventional (feat:, fix:, docs:, refactor:, test:, chore:)
- Refer to teammates by NAME, not agent ID
```
---
## ON `/vc:team research <topic>` [--researchers N]:
*Coordinates parallel `research-agent` teammates plus shared helper skills where useful.*
IMMEDIATELY execute in order:
1. **Derive N angles** from `<topic>` (default N=3):
- Angle 1: Architecture, patterns, proven approaches
- Angle 2: Alternatives, competing solutions, trade-offs
- Angle 3: Risks, edge cases, failure modes, security
- (If N>3, derive additional angles from topic context)
2. **CALL** `TeamCreate(team_name: "<topic-slug>")` after user approval to use agent teams
3. **CALL** `TaskCreate` x N -- one per angle:
- Subject: `Research: <angle-title>`
- Description: `Investigate <angle> for topic: <topic>. Save report to: {CK_REPORTS_PATH}/research-agent-{N}-{CK_NAME_PATTERN}-{topic-slug}.md. Format: Executive summary, key findings, evidence, contradictions, unresolved questions. Do not recommend implementations. Mark task completed when done. Send findings summary to lead.`
4. **SPAWN** teammates x N via `Agent` tool:
- `subagent_type: "research-agent"`, `model: "opus"`
- `run_in_background: true` (non-blocking -- spawn all N concurrently)
- `name: "research-agent-{N}"`
- Prompt: task description + CK Context Block
5. **MONITOR** via TaskCompleted hook events + TaskList fallback:
- TaskCompleted events auto-notify when `research-agent` subagents finish
- Fallback: Check TaskList if no event recComprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Use this agent when you need to investigate issues, analyze system behavior, diagnose performance problems, examine database structures, collect and analyze logs from servers or CI/CD pipelines, run tests for debugging purposes, or optimize system performance. This includes troubleshooting errors, identifying bottlenecks, analyzing failed deployments, investigating test failures, and creating diagnostic reports. Examples:\n\n<example>\nContext: The user needs to investigate why an API endpoint is returning 500 errors.\nuser: "The /api/users endpoint is throwing 500 errors"\nassistant: "I''ll use the debugger agent to investigate this issue"\n<commentary>\nSince this involves investigating an issue, use the Task tool to launch the debugger agent.\n</commentary>\n</example>\n\n<example>\nContext: The user wants to analyze why the CI/CD pipeline is failing.\nuser: "The GitHub Actions workflow keeps failing on the test step"\nassistant: "Let me use the debugger agent to analyze the CI/CD pipeline logs and identify the issue"\n<commentary>\nThis requires analyzing CI/CD logs and test failures, so use the debugger agent.\n</commentary>\n</example>\n\n<example>\nContext: The user notices performance degradation in the application.\nuser: "The application response times have increased by 300% since yesterday"\nassistant: "I''ll launch the debugger agent to analyze system behavior and identify performance bottlenecks"\n<commentary>\nPerformance analysis and bottleneck identification requires the debugger agent.\n</commentary>\n</example>
EXECUTE MODE - Implementing EXACTLY what was planned. Full tool access. Can only be invoked after explicit user confirmation. Use after plan is approved.
FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + INNOVATE + PLAN) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.
Stage, commit, and push code changes with conventional commits. Use when user says "commit", "push", or finishes a feature/fix.
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features/*/active/ only. Use after approach is decided.