Fabro Workflow Factory

This is proper workflow orchestration for AI agents, not another chatbot wrapper. You define pipelines as Graphviz DOT files with support for human approval gates, multi-model routing via CSS-like stylesheets, parallel execution, and automatic retry loops. The human gate pattern is especially clever: workflows pause at hexagon nodes until you run `fabro approve` or `fabro reject`, so agents handle the grunt work while you control the decision points. Model routing lets you assign Opus to planning nodes, Sonnet to implementation, and GPT-4o to review using class selectors. It's written in Rust, runs as a persistent service, and includes sandbox SSH access and cost retrospectives. If you're coordinating multi-step agent workflows rather than one-off prompts, this gives you the control plane you actually need.

skills.sh installs: 1.2K
GitHub stars: 61
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add aradotso/trending-skills --skill fabro-workflow-factory --agent claude-code

Installs into .claude/skills of the current project.

Files

Fabro Workflow Factory

Skill by ara.so — Daily 2026 Skills collection.

Fabro is an open source AI coding workflow orchestrator written in Rust. It lets you define agent pipelines as Graphviz DOT graphs — with branching, loops, human approval gates, multi-model routing, and cloud sandbox execution — then run them as a persistent service. You define the process; agents execute it; you intervene only where it matters.

Installation

# Via Claude Code (recommended)
curl -fsSL https://fabro.sh/install.md | claude

# Via Codex
codex "$(curl -fsSL https://fabro.sh/install.md)"

# Via Bash
curl -fsSL https://fabro.sh/install.sh | bash

After installation, run one-time setup and per-project initialization:

fabro install      # global one-time setup
cd my-project
fabro init         # per-project setup (creates .fabro/ config)

Key CLI Commands

# Workflow management
fabro run <workflow.dot>          # execute a workflow
fabro run <workflow.dot> --watch  # stream live output
fabro runs                        # list all runs
fabro runs show <run-id>          # inspect a specific run

SKILL.md on GitHub