ruflo
Ruflo is a multi-agent orchestration platform for AI coding agents (Claude Code, Cursor, Codex, Copilot, Gemini, Amp, +12 more).
Sorting a stream of records into a picture
What it does
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>.
Use this skill when the user wants to (1) install/init ruflo in a project, (2) run multi-agent swarms with hierarchical coordination, (3)…
You don’t need to name it. Ask for the job in your own words — your AI loads the skill when the request matches.
What it can touch
Includes 3782 scripts
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: .claude-plugin/scripts/install.sh, .claude-plugin/scripts/ruflo-hook.cjs, .claude-plugin/scripts/ruflo-hook.sh, .claude-plugin/scripts/uninstall.sh…; binary files: ruflo/src/ruvocal/static/wasm/rvagent_wasm_bg.wasm, v3/@claude-flow/cli/assets/model-router/seed-router.fastgrnn.safetensors, v3/@claude-flow/guidance/wasm-pkg/guidance_kernel_bg.wasm, v3/@claude-flow/watermark/wasm/ruflo_watermark_bg.wasm, v3/@claude-flow/watermark/web/ruflo_watermark_bg.wasm.
Turns off your AI's permission prompts
This weakens the protection between the skill and your computer, so later steps can happen without you being asked.
How we know
.agents/config.toml line 105 (and 1 more in that file): “approval_policy = "never"”. Read 2026-10-05, commit ad6a087.
.agents/config.toml, line 105 ↗Its code sends data over the internet
A script in it uploads or posts data. That is normal for a skill that talks to a service — check that the address is the service you expect.
How we know
.agents/skills/agent-code-review-swarm/SKILL.md line 354: “gh api --method POST $repos/:owner/:repo$pulls/123$comments -f path="$FILE" -f line="$LINE" -f body="$BODY" -f commit_id="$(gh pr vie…”. Read 2026-10-05, commit ad6a087.
.agents/skills/agent-code-review-swarm/SKILL.md, line 354 ↗Asks for administrator rights
Some of its commands use sudo or "run as administrator". Those can change anything on your computer.
How we know
Seen in its code. Read 2026-10-05, commit ad6a087.
Adds a connector (MCP server)
It sets up a separate program your AI can call. That program is not covered by this check.
How we know
An MCP configuration or "mcp add" command in its files. Read 2026-10-05, commit ad6a087.
4 smaller things worth knowing
Contains commands that delete or overwrite. Usually legitimate — listed so nothing is hidden.
How we know
Contains commands that delete or overwrite — .agents/skills/agent-tester/SKILL.md line 222; Contains commands that delete or overwrite — .agents/skills/hooks-automation/SKILL.md line 106; Contains commands that delete or overwrite — .agents/skills/verification-quality/SKILL.md line 650; Contains commands that delete or overwrite — .claude/agents/core/tester.md line 198. Read 2026-10-05, commit ad6a087.
.agents/skills/agent-tester/SKILL.md, line 222 ↗.agents/skills/hooks-automation/SKILL.md, line 106 ↗.agents/skills/verification-quality/SKILL.md, line 650 ↗.claude/agents/core/tester.md, line 198 ↗Partly checked
Launch7’s check could not read everything in this skill: 5 compiled program files it cannot read; 8 files too large to read; some files could not be downloaded in time. Nothing is known about the parts it skipped.
How we know
341 text files read; skipped files are listed by name only. Read 2026-10-05, commit ad6a087.
Its file has moved
The SKILL.md is no longer at the address this listing points to, so the download and install steps below may fail. The repository is still there — look for it under a new path.
How we know
GitHub returned 404 for the SKILL.md path on 2026-10-05; the repository itself answered.
Recently maintained
Its repository has had changes recently.
How we know
Last push to ruvnet/ruflo: 2026-10-05 (0 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 3782 scripts beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end
More from ruvnet
All from this publisher →- adr-index
After importing ADRs from another project - When the AgentDB graph is out of sync with the on-disk ADR files - Bootstrapping ADR tracking…
- adr-reindex
Reconcile the ADR index against a DELETED ADR file or relation line by dropping and rebuilding adr-patterns + adr-edges from scratch (scripts/reindex.mjs).
- AgentDB Advanced Features
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed…
- AgentDB Learning Plugins
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms.
- AgentDB Memory Patterns
Implement persistent memory patterns for AI agents using AgentDB.
