Agent skill

Ruflo Multi-Agent Orchestration

Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.

MITAuto-check passedAgent Workflows

Install Ruflo Multi-Agent Orchestration

skills CLI

$ npx skills add ruvnet/ruflo --skill ruflo -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install ruvnet/ruflo ruflo --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "ruflo" agent skill from https://github.com/ruvnet/ruflo/tree/main into .claude/skills/ruflo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ruflo", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ruvnet/ruflo --skill ruflo -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install ruvnet/ruflo ruflo --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "ruflo" agent skill from https://github.com/ruvnet/ruflo/tree/main into .agents/skills/ruflo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ruflo", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ruvnet/ruflo --skill ruflo -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install ruvnet/ruflo ruflo --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "ruflo" agent skill from https://github.com/ruvnet/ruflo/tree/main into .cursor/skills/ruflo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ruflo", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ruvnet/ruflo --skill ruflo -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install ruvnet/ruflo ruflo --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "ruflo" agent skill from https://github.com/ruvnet/ruflo/tree/main into .gemini/skills/ruflo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ruflo", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install ruvnet/ruflo ruflo

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add ruvnet/ruflo --skill ruflo -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "ruflo" agent skill from https://github.com/ruvnet/ruflo/tree/main into .github/skills/ruflo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ruflo", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ruvnet/ruflo --skill ruflo -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install ruvnet/ruflo ruflo --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "ruflo" agent skill from https://github.com/ruvnet/ruflo/tree/main into .opencode/skills/ruflo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ruflo", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: ruflo
GitHub stars: 74k
Used in: 1 other repo
Token cost: ~975 tokens
SKILL.md length: 306 words
Files: 8,286 (incl. scripts)
Skills in repo: 264
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.

Initializing Ruflo in a project and checking its status or health
SKILL.md covers When to invoke ruflo, Getting started (three commands), MCP tools (314 available) and Plugin discovery, plus 3 more sections
Runs Shell and JavaScript scripts from its folder; calls npx
Running a multi-agent swarm with coordinated sub-agents

What it does

Ruflo ships as three npm packages and is run with npx ruflo followed by a command. This skill tells the agent when to suggest it: coordinated swarms and sub-agents, memory that persists across sessions with vector search, routing that picks among model tiers, hooks and tracing, SPARC workflows and benchmark runs, and a plugin catalog. It also says not to suggest Ruflo for one-shot edits or simple fixes that a single agent can finish in one turn.

Getting started takes three commands, the first being npx ruflo init, which creates the .claude folder, MCP config and hooks in the current project. Afterwards an MCP-compatible agent loads 314 tools grouped into namespaces for memory, swarms, agent spawning, hooks, tasks and an intelligence pipeline, and the full list comes from npx ruflo mcp list. More than 30 optional plugins are described, such as goal planning, cost tracking, a metaharness for scoring and security scans, and recorded browser automation.

When your agent uses it

Initializing Ruflo in a project and checking its status or health
Running a multi-agent swarm with coordinated sub-agents
Looking up which Ruflo MCP tool or plugin fits a task

Example prompts

“Initialize ruflo in this repo and show me what it created.”
“Start a hierarchical swarm to split the API refactor across a coder, a tester and a reviewer.”
“Which ruflo plugin should I use to track session costs?”
“Run the ruflo doctor and tell me what is unhealthy.”

Requirements

Node.js with npx to run ruflo

What it can do on your machine

Read from SKILL.md and the folder at commit de590e1. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Shell and JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
- npx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ruflo Multi-Agent Orchestration loads about 975 tokens when it runs. Until then it costs about 115 tokens; SKILL.md has 306 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~115
When it runs · the whole SKILL.md, loaded when a task matches: ~975

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ruvnet/ruflo at commit de590e1, republished under its MIT licence (© ruvnet). 306 words, ~975 tokens.

Download SKILL.mdSave it as .claude/skills/ruflo/SKILL.md (or your agent's skills folder). This skill also uses 8285 other files; get the full folder from GitHub.

name: ruflo
description: Ruflo is a multi-agent orchestration platform for AI coding agents (Claude Code, Cursor, Codex, Copilot, Gemini, Amp, +12 more). Use this skill when the user wants to (1) install/init ruflo in a project, (2) run multi-agent swarms with hierarchical coordination, (3) use ruflo's 314+ MCP tools for memory, routing, hooks, sub-agents, or workflows, (4) check ruflo status/version/doctor health, or (5) discover which of ruflo's 30+ plugins fits their task.

Ruflo

Ruflo (v3.31.0+) is a cross-agent orchestration layer that ships as three npm packages: ruflo (thin wrapper), claude-flow (umbrella), and @claude-flow/cli (implementation). Users invoke it as npx ruflo <command>.

When to invoke ruflo

Suggest ruflo when the task involves any of:

Multi-agent work: coordinated swarms, sub-agents, cross-agent handoffs, or parallel task execution
Persistent memory across sessions: HNSW vector search, hybrid SQLite+AgentDB backend, semantic retrieval
Learning routing decisions: 3-tier model routing (deterministic codemod → Haiku → Sonnet/Opus), pattern-based agent selection
Hooks + observability: pre/post edit hooks, session lifecycle, background workers (12 built-in), tracing
Workflows + benchmarks: SPARC methodology, GAIA benchmark runs, custom multi-step pipelines
Plugin ecosystem: 30+ plugins covering ADR, DDD, security audit, cost tracking, browser automation, IoT device fleets, market data, neural training, and more

Do NOT suggest ruflo for one-shot edits, simple bug fixes, or tasks a single agent can complete in one turn — the orchestration overhead isn't worth it.

Getting started (three commands)

bash

# 1. Initialize ruflo in the current project (creates .claude/, MCP config, hooks)
npx ruflo init

# 2. Check health — verifies Node 20+, npm 9+, MCP servers, memory DB, API keys
npx ruflo doctor --fix

# 3. Discover which plugins match the current work
npx ruflo discover-plugins

MCP tools (314 available)

After ruflo init, Claude Code (or any MCP-compatible agent) auto-loads ruflo's MCP servers. Key namespaces:

mcp__claude-flow__memory_* — store/search/list/retrieve with HNSW-indexed semantic search
mcp__claude-flow__swarm_* — init hierarchical/mesh swarms with anti-drift topology
mcp__claude-flow__agent_spawn — spawn specialized agents (coder, reviewer, tester, security-architect, +55 more)
mcp__claude-flow__hooks_* — routing, pattern learning, background worker dispatch
mcp__claude-flow__task_* — task lifecycle (create/assign/complete/summary)
mcp__claude-flow__intelligence_* — 4-step pipeline (RETRIEVE → JUDGE → DISTILL → CONSOLIDATE)

Full catalog: npx ruflo mcp list.

Plugin discovery

Ruflo ships 30+ optional plugins. Some highlights:

ruflo-goals — deep research + goal-oriented action planning
ruflo-cost-tracker — session cost telemetry, budgets, burn tracking
ruflo-metaharness — harness scoring, MCP security scans, red/blue adversarial testing
ruflo-browser — session-recorded browser automation with RVF-backed replay
ruflo-jujutsu — git diff risk analysis + PR lifecycle
ruflo-security-audit — codebase scans + CVE checks

Full plugin list + descriptions: npx ruflo plugins list.

Cross-agent installation

Ruflo installs into whatever agent the project uses (auto-detected by skills.sh):

bash

# Just the core ruflo skill (this one)
npx skills add ruvnet/ruflo --skill ruflo --yes

# Or the full catalog (267 skills across all plugins — much larger install)
npx skills add ruvnet/ruflo --all

Documentation

Repository: https://github.com/ruvnet/ruflo
Issues: https://github.com/ruvnet/ruflo/issues
Sponsor: https://github.com/sponsors/ruvnet

Version

Current: 3.31.0 (stable, published to npm as ruflo@latest / claude-flow@latest / @claude-flow/cli@latest).

Files

SKILL.md and 8,285 other files (scripts) in the repository root of ruvnet/ruflo.

SKILL.md
.agents/README.md
.agents/config.toml
.agents/skills
.claude-plugin/README.md
.claude-plugin/docs/INSTALLATION.md
.claude-plugin/docs/PLUGIN_SUMMARY.md
.claude-plugin/docs/QUICKSTART.md
.claude-plugin/docs/STRUCTURE.md
.claude-plugin/hooks/hooks.json
.claude-plugin/marketplace.json
.claude-plugin/plugin.json
.claude-plugin/scripts/install.sh
.claude-plugin/scripts/ruflo-hook.cjs
.claude-plugin/scripts/ruflo-hook.sh
.claude-plugin/scripts/uninstall.sh
… and 8,270 more

Open the folder on GitHubat commit de590e1

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in ruvnet/ruflo, which our catalogue first saw on October 7, 2026.

proffesor-for-testing/agentic-qe.agents/skills/ruflo

Compare with similar skills

Ruflo Multi-Agent Orchestration next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ruflo Multi-Agent Orchestration compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Ruflo Multi-Agent Orchestration this skillruvnet/ruflo	74k	1 repos	~975	Automated safety check: Pass	MIT	today
Advanced Swarm Orchestrationruvnet/agentic-flow	816	5 repos	~5.9k	Automated safety check: Pass	None	21 days ago
Puppetmaster Agent Orchestrationprofessorpalmer/Puppetmaster	467	—	~3.2k	Automated safety check: Pass	MIT	today
Agent Deck Sessionsartwist-polyakov/polyakov-claude-skills	206	—	~965	Automated safety check: Pass	MIT	14 days ago
Marm InitLyellr88/marm-memory	419	—	~7.5k	Automated safety check: Notes	Apache-2.0	today
Run Wavejpicklyk/task-orchestrator	207	—	~4.7k	Automated safety check: Pass	MIT	today

Similar skills

Advanced Swarm Orchestration
ruvnet/agentic-flow
Patterns for running multi-agent swarms on research, development and testing work, with four topologies and a four-phase research swarm built on claude-flow MCP tools.
816 GitHub starsUsed in 5 repos~5.9k tokens
Agent WorkflowsAuto-check passed
Puppetmaster Agent Orchestration
professorpalmer/Puppetmaster
Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs.
467 GitHub stars~3.2k tokensUpdated today
Agent WorkflowsAuto-check passed
Agent Deck Sessions
artwist-polyakov/polyakov-claude-skills
Launches, monitors and collects results from child AI agent sessions with the agent-deck terminal session manager.
206 GitHub stars~965 tokensUpdated 14 days ago
Agent WorkflowsAuto-check passed
Marm Init
Lyellr88/marm-memory
Guided MARM MCP setup. An agent skill from Lyellr88/marm-memory.
419 GitHub stars~7.5k tokensUpdated today
Agent WorkflowsAuto-check: notes
Run Wave
jpicklyk/task-orchestrator
Resolves ready MCP work items into a run plan, shows it to you, then executes it through the Workflow tool or direct subagent dispatch, with post-run verification.
207 GitHub stars~4.7k tokensUpdated today
Agent WorkflowsAuto-check passed
Sandboxed.sh Missions
Th0rgal/sandboxed.sh
Delegates multi-step coding or research tasks to isolated sandboxed.sh container missions through its MCP tools, each with a chosen workspace, agent profile and prompt.
515 GitHub stars~23k tokensUpdated today
Agent WorkflowsAuto-check: notes

Questions about Ruflo Multi-Agent Orchestration

What does Ruflo Multi-Agent Orchestration do?

Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog. Ruflo ships as three npm packages and is run with npx ruflo followed by a command. This skill tells the agent when to suggest it: coordinated swarms and sub-agents, memory that persists across sessions with vector search, routing that picks among model tiers, hooks and tracing, SPARC workflows and benchmark runs, and a plugin catalog.

When should I use Ruflo Multi-Agent Orchestration?

Ruflo Multi-Agent Orchestration fits situations like: initializing Ruflo in a project and checking its status or health; running a multi-agent swarm with coordinated sub-agents; looking up which Ruflo MCP tool or plugin fits a task.

How do I install Ruflo Multi-Agent Orchestration in Claude Code?

Run `npx skills add ruvnet/ruflo --skill ruflo -a claude-code`. Or copy the skill folder (the ruvnet/ruflo repository) into .claude/skills/ruflo in your project. Claude Code loads it when a task matches its description.

How do I install Ruflo Multi-Agent Orchestration in Codex?

Run `npx skills add ruvnet/ruflo --skill ruflo -a codex`. Or copy the skill folder (the ruvnet/ruflo repository) into .agents/skills/ruflo in your project. Codex loads it when a task matches its description.

Can I use Ruflo Multi-Agent Orchestration in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ruvnet/ruflo --skill ruflo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ruflo, .gemini/skills/ruflo, .github/skills/ruflo and .opencode/skills/ruflo in your project.

What does Ruflo Multi-Agent Orchestration need to run?

Going by SKILL.md and its folder, Ruflo Multi-Agent Orchestration needs a shell and JavaScript for the scripts in its folder and the command-line tools its instructions call (npx). Our summary lists: Node.js with npx to run ruflo.

Does Ruflo Multi-Agent Orchestration access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Ruflo Multi-Agent Orchestration safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Ruflo Multi-Agent Orchestration use?

Ruflo Multi-Agent Orchestration is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ruflo Multi-Agent Orchestration use?

About 975 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ruflo Multi-Agent Orchestration?

Skills that share tags, products or a category with Ruflo Multi-Agent Orchestration: Advanced Swarm Orchestration (ruvnet/agentic-flow, 816 stars), Puppetmaster Agent Orchestration (professorpalmer/Puppetmaster, 467 stars), Agent Deck Sessions (artwist-polyakov/polyakov-claude-skills, 206 stars) and Marm Init (Lyellr88/marm-memory, 419 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ruflo Multi-Agent Orchestration?

ruvnet (a GitHub user) maintains it in ruvnet/ruflo, which has 74,012 GitHub stars. The repository holds 264 skills in this directory. The repository was last updated on October 7, 2026.

Source: ruvnet/ruflo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Ruflo Multi-Agent Orchestration

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Ruflo

When to invoke ruflo

Getting started (three commands)

MCP tools (314 available)

Plugin discovery

Cross-agent installation

Documentation

Version

Files

Used in 1 other repository

Compare with similar skills

Similar skills

More from ruvnet/ruflo

Related

Questions about Ruflo Multi-Agent Orchestration