ruflo: Skill for Claude Code

.agents/skills/flow-nexus-swarm/SKILL.md

flow-nexus-swarm is a skill for Claude Code, Codex from ruvnet/ruflo. It costs 20 tokens per session (4,226 once invoked), scanned A, original, MIT.

A cloud service for deploying groups of AI agents and running event-driven workflows. Event-driven means work starts when messages or other events arrive, while a swarm is a coordinated group of agents.

In plain words
What is it for?
Use it to create agent swarms, choose coordination topologies, assign agents, process message queues, and monitor workflows.
Why use it?
It organizes multi-agent jobs, asynchronous messages, monitoring, and scaling in a shared cloud environment.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); $skill-name invocation.

This is ruvnet/ruflo's own configuration. It tells Claude Code and Codex how to work on ruflo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ruflo configures →

Part of the claude-flow plugin — 134 skills, 52 commands, 11 agents, 4 hooks shipped together

not rated 72krepo +1.2k today A scan Socket: warnSnyk: warnSkillSpector: warn 20 tokens original MIT
About the project

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.

ruvnet/ruflo · 71,708 stars · on GitHub · cognitum.one

Reuse

Borrowing it

Nothing to install: this file belongs to ruvnet/ruflo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ruvnet/ruflo/main/.agents/skills/flow-nexus-swarm/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ruvnet/ruflo

Made for: Claude Code, Codex.

Or install claude-flow, the plugin that ships this one along with the rest of its 134 skills, 52 commands, 11 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.

agentmods badge for flow-nexus-swarm

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruvnet/ruflo/flow-nexus-swarm/github.svg)](https://agentmods.dev/skills/ruvnet/ruflo/flow-nexus-swarm)
Your own site
<a href="https://agentmods.dev/skills/ruvnet/ruflo/flow-nexus-swarm"><img src="https://agentmods.dev/badge/skills/ruvnet/ruflo/flow-nexus-swarm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for flow-nexus-swarm

Your own site · 80×15
<a href="https://agentmods.dev/skills/ruvnet/ruflo/flow-nexus-swarm"><img src="https://agentmods.dev/badge/skills/ruvnet/ruflo/flow-nexus-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,226 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket warn 18 Mar 2026
  • Snyk warn 1 Mar 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 593
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 596
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 599
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 553
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 556
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
Origin original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.04226
Opus 5 $0.00010 $0.02113
Sonnet 5 $0.00004 $0.00845
Haiku 4.5 $0.00002 $0.00423

Measured 6d ago against content hash f060e56109c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

flow-nexus-swarm 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 6d 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

Copies of this mod

5 near-identical copies found in the catalogue:

.agents/skills/flow-nexus-swarm/SKILL.md · 611 lines

How it starts

The opening of the file, as written. The whole thing — 611 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flow Nexus Swarm & Workflow Orchestration

Deploy and manage cloud-based AI agent swarms with event-driven workflow automation, message queue processing, and intelligent agent coordination.

📋 Table of Contents

  1. Overview
  2. Swarm Management
  3. Workflow Automation
  4. Agent Orchestration
  5. Templates & Patterns
  6. Advanced Features
  7. Best Practices

Overview

Flow Nexus provides cloud-based orchestration for AI agent swarms with:

  • Multi-topology Support: Hierarchical, mesh, ring, and star architectures
  • Event-driven Workflows: Message queue processing with async execution
  • Template Library: Pre-built swarm configurations for common use cases
  • Intelligent Agent Assignment: Vector similarity matching for optimal agent selection
  • Real-time Monitoring: Comprehensive metrics and audit trails
  • Scalable Infrastructure: Cloud-based execution with auto-scaling

Swarm Management

Initialize Swarm

Create a new swarm with specified topology and configuration:

mcp__flow-nexus__swarm_init({
  topology: "hierarchical", // Options: mesh, ring, star, hierarchical
  maxAgents: 8,
  strategy: "balanced" // Options: balanced, specialized, adaptive
})

Topology Guide:

  • Hierarchical: Tree structure with coordinator nodes (best for complex projects)
  • Mesh: Peer-to-peer collaboration (best for research and analysis)
  • Ring: Circular coordination (best for sequential workflows)
  • Star: Centralized hub (best for simple delegation)

Strategy Guide:

  • Balanced: Equal distribution of workload across agents
  • Specialized: Agents focus on specific expertise areas
  • Adaptive: Dynamic adjustment based on task complexity

Spawn Agents

Add specialized agents to the swarm:

mcp__flow-nexus__agent_spawn({
  type: "researcher", // Options: researcher, coder, analyst, optimizer, coordinator
  name: "Lead Researcher",
  capabilities: ["web_search", "analysis", "summarization"]
})

Read the full file on GitHub · 611 lines

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.

  1. 6d ago First seen · 611 lines · 20 tokens per session scan A f060e56109c5

Subscribe to this mod's changes

flow-nexus-swarm is a skill published in the GitHub repository ruvnet/ruflo (71,708 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 4,226 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.