What is smart-agents?

A system that chooses and starts agents automatically based on the files being edited and the complexity of the task. An agent is a specialized AI worker, such as one for coding, research, or testing.

Use it to assign agents for JavaScript, TypeScript, Markdown, JSON, YAML, or multi-file work, and to scale from a simple task to a larger task involving architecture, coding, testing, and research.

It removes the need to decide manually which agents to start and when more help is needed.

smart-agents — Command for Claude Code by EarthmanWeb: A system that chooses and starts agents automatically based…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/earthmanweb/claude-flow-plugin/smart-agents

Clone the repo

git clone --depth 1 https://github.com/EarthmanWeb/claude-flow-plugin

Made for: Claude Code.

Or install claude-flow, the plugin that ships this one along with the rest of its 47 commands, 7 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/earthmanweb/claude-flow-plugin/smart-agents.svg)](https://agentmods.dev/commands/earthmanweb/claude-flow-plugin/smart-agents)

Your own site

<a href="https://agentmods.dev/commands/earthmanweb/claude-flow-plugin/smart-agents"><img src="https://agentmods.dev/badge/commands/earthmanweb/claude-flow-plugin/smart-agents.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 393 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00393
Opus 5	$0.00000	$0.00197
Sonnet 5	$0.00000	$0.00079
Haiku 4.5	$0.00000	$0.00039

Measured 3d ago against content hash 238825c0f83e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

smart-agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to smart-agents — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/automation/smart-agents.md · 73 lines

What it actually says

Smart Agent Auto-Spawning

Purpose

Automatically spawn the right agents at the right time without manual intervention.

Auto-Spawning Triggers

1. File Type Detection

When editing files, agents auto-spawn:

JavaScript/TypeScript: Coder agent
Markdown: Researcher agent
JSON/YAML: Analyst agent
Multiple files: Coordinator agent

2. Task Complexity

Simple task: "Fix typo"
→ Single coordinator agent

Complex task: "Implement OAuth with Google"
→ Architect + Coder + Tester + Researcher

3. Dynamic Scaling

The system monitors workload and spawns additional agents when:

Task queue grows
Complexity increases
Parallel opportunities exist

Status Monitoring:

// Check swarm health
mcp__claude-flow__swarm_status({
  "swarmId": "current"
})

// Monitor agent performance
mcp__claude-flow__agent_metrics({
  "agentId": "agent-123"
})

Configuration

MCP Tool Integration

Uses Claude Flow MCP tools for agent coordination:

// Initialize swarm with appropriate topology
mcp__claude-flow__swarm_init({
  "topology": "mesh",
  "maxAgents": 8,
  "strategy": "auto"
})

// Spawn agents based on file type
mcp__claude-flow__agent_spawn({
  "type": "coder",
  "name": "JavaScript Handler",
  "capabilities": ["javascript", "typescript"]
})

Fallback Configuration

If MCP tools are unavailable:

npx claude-flow hook pre-task --auto-spawn-agents

Benefits

🤖 Zero manual agent management
🎯 Perfect agent selection
📈 Dynamic scaling
💾 Resource efficiency

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 73 lines · 0 tokens per session scan A 238825c0f83e

Subscribe to this mod's changes

smart-agents is a command published in the GitHub repository EarthmanWeb/claude-flow-plugin (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 393 tokens. A static security scan graded it A with 0 findings. It is 100% identical to smart-agents, differing in 0 lines, and is treated as a copy.

Building agents

smart-agents