Summary
This handles the full lifecycle of running workflows in two different modes. For MCP workflows, you get execute, pause, resume, cancel, and status operations with support for sequential, parallel, conditional, and manual gate execution. For native .claude/workflows/*.js files, it invokes the Workflow tool and manages deterministic subagent fan-outs with journal-based resume from a prior runId. The MCP side is stateful orchestration, the native side is cached replay. Use it when you need to actually run a workflow you've already defined, not just create or inspect one. The two surfaces don't share a pause mechanism, which is a bit awkward but reflects the underlying architecture.
Install to Claude Code
npx -y skills add ruvnet/ruflo --skill workflow-run --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
