An orchestration plugin for running many specialized AI agents, coordinating their work, following the SPARC development method, integrating with GitHub, and training neural models.

Use it to delegate work to specialized agents, run coordinated swarms, automate GitHub-related tasks, follow SPARC workflows, and support test-driven development and code review.

It brings agent coordination and development workflows into one system instead of requiring separate manual steps.

claude-flow — Plugin for Claude Code and Codex by proffesor-for-testing: An orchestration plugin for running many specialized AI agents…

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.

Claude Code

/plugin marketplace add proffesor-for-testing/agentic-qe

agentmods

npx agentmods add plugins/proffesor-for-testing/agentic-qe/ruflo

Clone the repo

git clone --depth 1 https://github.com/proffesor-for-testing/agentic-qe

Made for: Claude Code, Codex.

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/plugins/proffesor-for-testing/agentic-qe/ruflo.svg)](https://agentmods.dev/plugins/proffesor-for-testing/agentic-qe/ruflo)

Your own site

<a href="https://agentmods.dev/plugins/proffesor-for-testing/agentic-qe/ruflo"><img src="https://agentmods.dev/badge/plugins/proffesor-for-testing/agentic-qe/ruflo.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 134 skills, 46 commands, 11 agents, 4 hooks cost 3,996 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

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

Security

Grade A, and why

claude-flow 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.

The scan reads plugin.json. This mod also ships 5 executable files (scripts/install.sh, scripts/ruflo-hook.cjs, scripts/ruflo-hook.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 claude-flow — 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.

.agents/skills/ruflo/.claude-plugin/plugin.json · 72 lines

What it actually says

{
  "name": "claude-flow",
  "version": "2.5.0",
  "description": "Enterprise AI agent orchestration plugin with 150+ commands, 74+ specialized agents, SPARC methodology, swarm coordination, GitHub integration, and neural training capabilities",
  "author": {
    "name": "rUv",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/ruvnet/claude-flow",
  "repository": {
    "type": "git",
    "url": "https://github.com/ruvnet/claude-flow.git"
  },
  "bugs": {
    "url": "https://github.com/ruvnet/claude-flow/issues"
  },
  "license": "MIT",
  "keywords": [
    "ai-agents",
    "swarm-intelligence",
    "orchestration",
    "sparc-methodology",
    "github-automation",
    "neural-training",
    "mcp-integration",
    "enterprise",
    "workflow-automation",
    "multi-agent",
    "coordination",
    "tdd",
    "code-review",
    "performance-optimization"
  ],
  "category": "development",
  "tags": [
    "productivity",
    "automation",
    "ai",
    "agents",
    "swarm",
    "coordination",
    "sparc",
    "github",
    "neural-network",
    "enterprise"
  ],
  "engines": {
    "claudeCode": ">=2.0.0",
    "node": ">=20.0.0"
  },
  "mcpServers": {
    "claude-flow": {
      "command": "npx",
      "args": ["claude-flow@alpha", "mcp", "start"],
      "description": "Core Claude Flow MCP server for swarm coordination, agent management, and task orchestration (40+ tools)",
      "optional": false
    },
    "ruv-swarm": {
      "command": "npx",
      "args": ["ruv-swarm", "mcp", "start"],
      "description": "Enhanced swarm coordination with WASM acceleration (2.8-4.4x speed improvement)",
      "optional": true
    },
    "flow-nexus": {
      "command": "npx",
      "args": ["flow-nexus@latest", "mcp", "start"],
      "description": "Cloud-based orchestration platform with 70+ tools (requires authentication)",
      "optional": true
    }
  }
}

Contents

What it installs

The manifest is a name and a version. 134 skills, 46 commands, 11 agents, 4 hooks travel with it, and installing the plugin installs all of them — 3,996 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

12 files beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday First seen · 72 lines scan A 2c65ee65f718

Subscribe to this mod's changes

claude-flow is a plugin published in the GitHub repository proffesor-for-testing/agentic-qe (473 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. It is 100% identical to claude-flow, differing in 0 lines, and is treated as a copy.

Building agents Productivity agenticqe agenticsfoundation agents quality-engineering

verefi

AI-assisted pipeline that turns product specs into human-reviewed test plans and executable Playwright automation.

philchen00/verefi · not measured

quality-skills

Quality engineering skills for QA engineers, SDETs, and test automation leads — covering frontend (Selenium/Cypress/Playwright), API (Postman/REST Assured/Karate), performance (k6/JMeter/Gatling), mobile (Appium), BDD, accessibility, visual regression, security, chaos, contract testing, CI orchestration, and quality…

aks-builds/quality-skills · not measured

claude-flow

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

This is a copy

What it actually says

What it installs

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

verefi

quality-skills

nextjs

claude-plugins-official marketplace

humanizer

knowledge-work-plugins marketplace