/swarm-cli
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.
$ npx -y skills add joelhooks/swarm-tools --skill swarm-cli --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/swarm-cli
Context preview
The summary Claude sees to decide when to auto-load this skill.
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.
SKILL.md
swarm-cli.SKILL.mdname: swarm-cli
description: |
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.
Swarm CLI Quick Reference
Memory (Hivemind)
swarm memory find "query" # Semantic search for learnings
swarm memory find "query" --fts # Full-text search fallback
swarm memory store "info" --tags x # Store a learning
swarm memory get <id> # Get specific memory
swarm memory stats # Check memory health
**When to query:**
- BEFORE starting any task - check for existing solutions
- When stuck - search for similar problems
- Before major decisions - find past rationale
**When to store:**
- Solved a tricky bug (>15min debugging)
- Found a project-specific pattern
- Discovered a tool/library gotcha
- Made an architectural decision
Task Tracking (Hive)
swarm hive ready # Get next unblocked task
swarm hive query --status open # List open tasks
swarm hive create "title" --type bug --priority 1
swarm hive update <id> --status in_progress
swarm hive close <id> "summary" # Close completed task
swarm tree # Visualize task hierarchy
Coordination (Swarm Mail)
swarm mail inbox # Check for messages
swarm mail send "coordinator" "Subject" "Body"
swarm mail reserve file.ts # Reserve file for editing
swarm mail release # Release all reservations
Progress & Checkpoints
swarm progress 50 "message" # Report 50% progress
swarm checkpoint # Save context before risky ops
swarm complete "summary" # Mark task done (releases locks)
Analytics
swarm compliance # Check tool usage stats
swarm history # Recent swarm activity
swarm dashboard # Live worker status UI
Core Workflow
1. `swarm memory find "<task keywords>"` - Check for existing solutions 2. `swarm hive ready` - Get your task 3. `swarm mail reserve <files>` - Lock your files 4. Do the work (TDD: red → green → refactor) 5. `swarm progress 50 "message"` - Report milestones 6. `swarm memory store "learning" --tags "domain"` - Store discoveries 7. `swarm complete "summary"` - Finish and release locks
Tips
- **Query before coding** - 90% of problems have been solved before
- **Store actionable learnings** - Include WHY, not just WHAT
- **Reserve files early** - Prevents edit conflicts with other workers
- **Report progress** - Silent workers look stuck
- **Checkpoint before risky ops** - Saves context for recovery
Read more
name: swarm-cli description: | 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.
Swarm CLI Quick Reference
Memory (Hivemind)
swarm memory find "query" # Semantic search for learnings swarm memory find "query" --fts # Full-text search fallback swarm memory store "info" --tags x # Store a learning swarm memory get <id> # Get specific memory swarm memory stats # Check memory health
**When to query:**
- BEFORE starting any task - check for existing solutions
- When stuck - search for similar problems
- Before major decisions - find past rationale
**When to store:**
- Solved a tricky bug (>15min debugging)
- Found a project-specific pattern
- Discovered a tool/library gotcha
- Made an architectural decision
Task Tracking (Hive)
swarm hive ready # Get next unblocked task swarm hive query --status open # List open tasks swarm hive create "title" --type bug --priority 1 swarm hive update <id> --status in_progress swarm hive close <id> "summary" # Close completed task swarm tree # Visualize task hierarchy
Coordination (Swarm Mail)
swarm mail inbox # Check for messages swarm mail send "coordinator" "Subject" "Body" swarm mail reserve file.ts # Reserve file for editing swarm mail release # Release all reservations
Progress & Checkpoints
swarm progress 50 "message" # Report 50% progress swarm checkpoint # Save context before risky ops swarm complete "summary" # Mark task done (releases locks)
Analytics
swarm compliance # Check tool usage stats swarm history # Recent swarm activity swarm dashboard # Live worker status UI
Core Workflow
1. `swarm memory find "<task keywords>"` - Check for existing solutions 2. `swarm hive ready` - Get your task 3. `swarm mail reserve <files>` - Lock your files 4. Do the work (TDD: red → green → refactor) 5. `swarm progress 50 "message"` - Report milestones 6. `swarm memory store "learning" --tags "domain"` - Store discoveries 7. `swarm complete "summary"` - Finish and release locks
Tips
- **Query before coding** - 90% of problems have been solved before
- **Store actionable learnings** - Include WHY, not just WHAT
- **Reserve files early** - Prevents edit conflicts with other workers
- **Report progress** - Silent workers look stuck
- **Checkpoint before risky ops** - Saves context for recovery
Multi-agent coordination that survives context death. Break big tasks into small ones. Spawn agents to work in parallel. Learn from what works. swarmtools.ai · Documentation
Repo: joelhooks/swarm-tools
Other skills on swarm-tools.
- /release
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
Open skill - /always-on-guidance
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.
Open skill - /openclaw-messaging
Send 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
Open skill - /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.
Open skill - /always-on-guidance
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.
Open skill - /ralph-supervisor
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,
Open skill

