メニュー
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/athola/claude-night-market --skill agent-teamsコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Turn hunches into accepted results: worthiness score, evidence bar, research-to-rules. Use when vetting ideas. Not for QA; use night-market-validation-and-qa.
Generates and self-executes a diff-derived test plan for a PR. Use when validating PR changes before merge. Do not use for code review; use sanctum:pr-review.
Curate the web-capture index. Use when the capture backlog grows, captures sit unprocessed at seedling/pending, or to surface stored research during work.
SKILL.md を表示中
SOC 職業分類に基づく
| name | agent-teams |
| description | Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks. |
| alwaysApply | false |
| category | delegation-framework |
| tags | ["agent-teams","multi-agent","coordination","tmux","task-management","messaging"] |
| dependencies | ["delegation-core","leyline:damage-control","leyline:risk-classification"] |
| tools | [] |
| usage_patterns | ["team-orchestration","parallel-implementation","multi-agent-review","task-dependency-management"] |
| complexity | advanced |
| model_hint | deep |
| estimated_tokens | 450 |
| progressive_loading | true |
| modules | ["modules/team-management.md","modules/messaging-protocol.md","modules/task-coordination.md","modules/spawning-patterns.md","modules/crew-roles.md","modules/health-monitoring.md"] |
| references | ["../../../leyline/skills/error-patterns/SKILL.md","../../../leyline/skills/service-registry/SKILL.md","references/team-formation.md"] |
Claude Code Agent Teams enables multiple Claude CLI processes to collaborate on shared work through a filesystem-based coordination protocol. Each teammate runs as an independent claude process in a tmux pane, communicating via JSON files guarded by fcntl locks, with no database, daemon, or network layer.
This skill provides the patterns for orchestrating agent teams effectively.
claude CLI is not available or tmux is not installed# Verify Claude Code CLI
claude --version
# Verify tmux (required for split-pane mode)
tmux -V
# Enable experimental feature (set by spawner automatically)
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
~/.claude/
teams/<team-name>/
config.json # Team metadata + member roster
inboxes/
<agent-name>.json # Per-agent message queue
.lock # fcntl exclusive lock
tasks/<team-name>/
1.json ... N.json # Auto-incrementing task files
.lock # fcntl exclusive lock
Design principles:
tempfileos.replace# Programmatic team setup (via MCP or direct API)
# Team config written to ~/.claude/teams/<team-name>/config.json
The team config contains:
name, description, created_at (ms timestamp)lead_agent_id, lead_session_idmembers[]: array of LeadMember and TeammateMember objectsEach teammate is a separate claude CLI process launched with identity flags:
claude --agent-id "backend@my-team" \
--agent-name "backend" \
--team-name "my-team" \
--agent-color "#FF6B6B" \
--parent-session-id "$SESSION_ID" \
--agent-type "general-purpose" \
--model sonnet
See modules/spawning-patterns.md for tmux pane management and color assignment.
{
"id": "1",
"subject": "Implement API endpoints",
"description": "Create REST endpoints for user management",
"status": "pending",
"owner": null,
"blocks": ["3"],
"blocked_by": [],
"metadata": {}
}
See modules/task-coordination.md for state machine and dependency management.
{
"from": "team-lead",
"text": "API endpoints are ready for integration testing",
"timestamp": "2026-02-07T22:00:00Z",
"read": false,
"summary": "API ready"
}
See modules/messaging-protocol.md for message types and inbox operations.
agent-teams:team-created: Initialize team config and directoriesagent-teams:teammates-spawned: Launch agents in tmux panesagent-teams:tasks-assigned: Create tasks with dependencies, assign ownersagent-teams:coordination-active: Agents claim tasks, exchange messages, mark completionagent-teams:team-shutdown: Graceful shutdown with approval protocolEach team member has a role that determines their capabilities and task
compatibility. Five roles are defined: implementer (default), researcher,
tester, reviewer, and architect. Roles constrain which risk tiers an
agent can handle. See modules/crew-roles.md for the full capability matrix
and role-risk compatibility table.
For mission-level team sizing, use the Team Formation rules
from references/team-formation.md. This defines:
See references/team-formation.md for full team sizing
guidance and example team formations.
Team members can be monitored for health via heartbeat messages and claim expiry. The lead polls team health every 60s with a 2-stage stall detection protocol (health_check probe and 30s wait). Stalled agents have their tasks released and are restarted or replaced following the "replace don't wait" doctrine. See modules/health-monitoring.md for the full protocol and state machine.
Agent Teams extends the conjure delegation model:
| Conjure Pattern | Agent Teams Equivalent |
|---|---|
delegation-core:task-assessed | agent-teams:team-created |
delegation-core:handoff-planned | agent-teams:tasks-assigned |
delegation-core:results-integrated | agent-teams:team-shutdown |
| External LLM execution | Teammate agent execution |
Use Skill(conjure:delegation-core) first to determine if the task benefits from multi-agent coordination vs. single-service delegation.
For parallel agents that modify files, isolation: worktree provides a lightweight alternative to filesystem-based coordination. Each agent runs in its own temporary git worktree, eliminating the need for fcntl locking or inbox-based conflict avoidance on shared files.
isolation: worktree per teammate for filesystem safetytmux not found
Install via package manager: brew install tmux / apt install tmux
Stale lock files
If an agent crashes mid-operation, lock files may persist. Remove .lock files manually from ~/.claude/teams/<team>/inboxes/ or ~/.claude/tasks/<team>/
Orphaned tasks
Tasks claimed by a crashed agent stay in_progress indefinitely. Use modules/health-monitoring.md for heartbeat-based stall detection and automatic task release. The health monitoring protocol detects unresponsive agents within 60s and 30s probe window and releases their tasks for reassignment.
Message ordering Filesystem timestamp resolution varies (HFS+ = 1s granularity). Use numbered filenames or UUID-sorted names to avoid collision on rapid message bursts.
Model errors on Bedrock/Vertex/Foundry (pre-2.1.39) Teammate agents could use incorrect model identifiers on enterprise providers, causing 400 errors. Upgrade to Claude Code 2.1.39+ for correct model ID qualification across all providers.
Nested session guard (2.1.39+)
If claude refuses to launch within an existing session, ensure you're using
tmux pane splitting (not subshell invocation). The guard is intentional. See
modules/spawning-patterns.md for details.