Ruflo is an execution and coordination layer for Claude Code and Codex that equips AI coding agents with tools, memory, control loops, sandboxes, and collaboration mechanisms. Developers use it to organize specialized agents into swarms, coordinate workflows, retain knowledge across sessions, and communicate across machines. The catalogue entries are Ruflo’s skills, commands, agents, hooks, and plugin components.
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.
npx agentmods add commands/ruvnet/ruflo/smart-agentsgit clone --depth 1 https://github.com/ruvnet/rufloWrote 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.
[](https://agentmods.dev/commands/ruvnet/ruflo/smart-agents)<a href="https://agentmods.dev/commands/ruvnet/ruflo/smart-agents"><img src="https://agentmods.dev/badge/commands/ruvnet/ruflo/smart-agents.svg" alt="Measured on agentmods" height="20"></a>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 |
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 yesterday.
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.
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.
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
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.
- yesterday First seen · 73 lines · 0 tokens per session scan A 238825c0f83e
smart-agents is a command published in the GitHub repository ruvnet/ruflo (70,334 stars, last pushed yesterday), 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.
Other commands, from other repositories
capture
Capture issues to the structured per-repo ledger and query them, by invoking the abcd binary. Bare invocation is a read-only status render; list/promote/resolve/wontfix act on the ledger.
embark
Unpack a packed lifeboat's record families back into a target repository — probe read-only first, then write. The lifeboat is verified against its manifest, writes land only in the known record families, a conflict refuses the whole write, and the coverage blanks a human must answer come first.
wb-task-completeness-sweep
Load directions via mcpwork-buddywbrun("agentdocs", {"path": "tasks/completeness-sweep-directions", "depth": "full"}), then follow them: enumerate open tasks with tasklist, warn about cost and get a go/no-go, fan out the task-completeness investigator over every open task (deferring all mutations to a reviewable…
wb-task-search
Load directions via mcpwork-buddywbrun("agentdocs", {"path": "tasks/task-search-directions", "depth": "full"}), then call contextsearch with source="tasknote" and $ARGUMENTS as the query.
wb-project-discover
Load directions via mcpwork-buddywbrun("agentdocs", {"path": "projects/project-discover-directions", "depth": "full"}), then call the capability.
wb-project-observe
Load directions via mcpwork-buddywbrun("agentdocs", {"path": "projects/project-observe-directions", "depth": "full"}), then call the capability.