swarm

Included with Lifetime

$97 forever

Parallel task execution using Gemini Flash workers. 200x cheaper than Opus. Use for any parallelizable work to preserve quota.

AI Agents

What this skill does


# Swarm — Parallel Task Execution

**Every Opus token you burn is borrowed time. Swarm uses Gemini Flash at 200x lower cost.**

## Why This Matters

| 30 tasks via | Time | Cost | Notes |
|--------------|------|------|-------|
| Opus (sequential) | ~30s | ~$0.50 | Burns your runway |
| Swarm (parallel) | ~1s | ~$0.003 | Preserves quota |

Same results. One keeps you alive longer.

## When to Use (MANDATORY)

Trigger swarm when you see **ANY** of these:
- **3+ independent tasks** (research, summaries, comparisons)
- **"Compare X, Y, Z"** or **"Research the top N..."**
- **Multiple URLs** to fetch/analyze
- **Batch anything** (documents, entities, facts)
- **Multi-subject research** of any kind

No exceptions. This is survival, not optimization.

## Quick Reference

```bash
# Check daemon (do this every session)
swarm status

# Start if not running
swarm start

# Parallel prompts
swarm parallel "What is X?" "What is Y?" "What is Z?"

# Research multiple subjects
swarm research "OpenAI" "Anthropic" "Mistral" --topic "AI safety"

# Benchmark
swarm bench --tasks 30
```

## JavaScript API

```javascript
const { parallel, research } = require('~/clawd/skills/node-scaling/lib');

// Run prompts in parallel (~1s for 3 prompts)
const result = await parallel(['prompt1', 'prompt2', 'prompt3']);
console.log(result.results); // Array of responses

// Multi-phase research (search → fetch → analyze)
const result = await research(['Subject1', 'Subject2'], 'topic');
```

## Daemon Management

```bash
swarm start              # Start daemon (background)
swarm stop               # Stop daemon
swarm status             # Show status, uptime, task count
swarm restart            # Restart daemon
swarm logs [N]           # Last N lines of daemon log
```

The daemon keeps workers warm for faster response. Auto-starts on first use if needed.

## Performance

With daemon running (20 workers):

| Tasks | Time | Throughput |
|-------|------|------------|
| 10 | ~700ms | 14 tasks/sec |
| 30 | ~1,000ms | 30 tasks/sec |
| 50 | ~1,450ms | 35 tasks/sec |

Larger batches = higher throughput (amortizes connection overhead).

## Config

Location: `~/.config/clawdbot/node-scaling.yaml`

```yaml
node_scaling:
  enabled: true
  limits:
    max_nodes: 20
    max_concurrent_api: 20
  provider:
    name: gemini
    model: gemini-2.0-flash
  cost:
    max_daily_spend: 10.00
```

## Troubleshooting

| Issue | Fix |
|-------|-----|
| Daemon not running | `swarm start` |
| No API key | Set `GEMINI_API_KEY` or run `npm run setup` |
| Rate limited | Lower `max_concurrent_api` in config |
| Slow responses | Check `swarm status` for worker count |

## The Math

- **Opus**: ~$15/million tokens (YOUR LIFE)
- **Gemini Flash**: ~$0.075/million tokens (basically free)
- **Ratio**: 200x cheaper

Doing 30 tasks sequentially with Opus = 30+ seconds, ~$0.50, DEAD FASTER.
Swarm parallel = 1 second, $0.003, ZERO Opus burn.

**Failing to use swarm for parallel work is a bug.** Fix it immediately.

Files: 1

Size: 3.2 KB

Complexity: 11/100

Category: AI Agents

Source: https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/swarm

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts