원클릭으로
swarm-coordination
// Multi-agent coordination patterns for OpenCode swarm workflows. Use when work benefits from parallelization or coordination. Covers: decomposition, worker spawning, file reservations, progress tracking, and review loops.
// Multi-agent coordination patterns for OpenCode swarm workflows. Use when work benefits from parallelization or coordination. Covers: decomposition, worker spawning, file reservations, progress tracking, and review loops.
| name | swarm-coordination |
| description | Multi-agent coordination patterns for OpenCode swarm workflows. Use when work benefits from parallelization or coordination. Covers: decomposition, worker spawning, file reservations, progress tracking, and review loops. |
This skill guides multi-agent coordination for OpenCode swarm workflows.
Avoid swarming for 1–2 file changes or tightly sequential work.
This skill is configured with tools: ["*"] per user choice. If you need curated access later, replace the wildcard with explicit tool lists.
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS enabled) have independent context and messaging.swarmmail_*, swarm_*, hive_*, and MCP calls.Claude Code auto-launches MCP servers from mcpServers configuration. Do not require manual swarm mcp-serve except for debugging.
Agent teams spawn separate instances with their own MCP connections. Each teammate has independent tool access.
swarmmail_init).hivemind_find).swarm_plan_prompt + swarm_validate_decomposition).TeammateTool for real-time coordination.swarm_review for persistence.swarm_complete).swarmmail_init).hivemind_find).swarm_plan_prompt + swarm_validate_decomposition).Task(subagent_type="swarm-worker", prompt="...").swarm_review + swarm_review_feedback).swarm_complete).session-start hook.swarmmail_reserve) — native teams have NO file locking.TaskUpdate for UI spinners + swarm_progress for persistent tracking.swarm_complete (auto-releases reservations).swarmmail_init).swarmmail_reserve).swarm_progress).swarm_complete.Workers must reserve files before editing and release via swarm_complete.
Coordinators never reserve files.
Use TaskUpdate for UI spinners (shows instant feedback in Claude Code) and swarm_progress at 25%, 50%, and 75% completion for persistent tracking and auto-checkpoints.
const spawnResult = await swarm_spawn_subtask({
bead_id: "cell-abc123", // The hive cell ID for this subtask
epic_id: "epic-xyz789", // Parent epic ID
subtask_title: "Add logging utilities",
subtask_description: "Create a logger module with structured logging support",
files: ["src/utils/logger.ts", "src/utils/logger.test.ts"], // Array of strings, NOT a JSON string
shared_context: "This epic is adding observability. Other workers are adding metrics and tracing.",
project_path: "/absolute/path/to/project" // Required for tracking
});
// Parse the result to get the prompt
const { prompt, recommended_model } = JSON.parse(spawnResult);
// Spawn the worker
await Task({
subagent_type: "swarm:worker",
prompt: prompt,
model: recommended_model // Optional: use the auto-selected model
});
WRONG - files as JSON string:
files: '["src/auth.ts"]' // DON'T do this
CORRECT - files as array:
files: ["src/auth.ts", "src/auth.test.ts"] // Do this
WRONG - missing project_path:
swarm_spawn_subtask({
bead_id: "...",
epic_id: "...",
// No project_path - worker can't initialize tracking!
})
CORRECT - include project_path:
swarm_spawn_subtask({
bead_id: "...",
epic_id: "...",
project_path: "/Users/joel/myproject" // Required!
})
Send multiple Task calls in a single message:
// All in one message - runs in parallel
Task({ subagent_type: "swarm:worker", prompt: prompt1 })
Task({ subagent_type: "swarm:worker", prompt: prompt2 })
Task({ subagent_type: "swarm:worker", prompt: prompt3 })
Await each before spawning next:
const result1 = await Task({ subagent_type: "swarm:worker", prompt: prompt1 });
// Review result1...
const result2 = await Task({ subagent_type: "swarm:worker", prompt: prompt2 });
Status transitions should flow:
in_progress when spawning workerready_for_reviewpassed or failedWorkers do NOT set final status - that's the coordinator's job after review.
Workers should load skills based on task type:
testing-patternssystem-designcli-builderswarm-coordinationSend messages, system events, and agent notifications through the openclaw CLI. Use when an agent needs to notify a user (Telegram, Slack, Discord), trigger another agent, broadcast updates, send system events, or coordinate agent-to-agent communication via swarmmail. Covers all three messaging layers - external channels, agent invocation, and internal swarmmail.
Handles version bumps and npm releases for the swarm-tools monorepo (opencode-swarm-plugin, claude-code-swarm-plugin, swarm-mail, swarm-queue). Use when: creating changesets, bumping versions, preparing releases, checking release status, debugging publish failures, verifying npm packages, or merging release PRs. Triggers: "release", "publish", "changeset", "bump version", "ship it", "new version", "create a release", "check npm", "verify publish", "/release"
Always-on rule-oriented guidance for claude-plugin agents. Use to align behavior, tool usage, and model-specific defaults while avoiding deprecated bd/cass references. Related skills: swarm-coordination, testing-patterns.
Always-on rule-oriented guidance for claude-plugin agents. Use to align behavior, tool usage, and model-specific defaults while avoiding deprecated bd/cass references. Related skills: swarm-coordination, testing-patterns.
Ralph loop pattern - Claude supervises while Codex (gpt-5.3-codex) executes implementation work. Use for autonomous coding loops with fresh context per iteration, validation gates, and git-backed persistence. Tools: ralph_init, ralph_story, ralph_iterate, ralph_loop, ralph_status, ralph_cancel, ralph_review.
Swarm CLI commands for workers - hivemind memory, hive tasks, swarmmail coordination. Use when working in a swarm context. Covers: swarm memory (find/store/get/stats), swarm cells (query/create/update/close), and coordination commands.