frago

🥈Silver

Multi-runtime automation infrastructure for AI agents. Enables native CDP browser control, metadata-driven Recipe system, and persistent Run context management. Ideal for operations teams automating workflows with AI agents.

5470Updated 2mo ago

Intermediate30min to implementautomation

Saves ~135 min per use

Quick InstallView Source

git clone https://github.com/tsaijamey/frago.git

Works with:

Claude

Overview

About This Skill

How to Use

[{"step":"Define your workflow as a frago Recipe in YAML. Use `frago.recipe.template` as a starting point for common patterns (e.g., web scraping, API polling, or data transformation). Include error handlers for each step to ensure resilience.","tip":"Use frago’s VS Code extension to validate your Recipe syntax and preview outputs before execution."},{"step":"Configure runtime environments (e.g., `DEV`, `PROD`) with secrets and endpoints. Store sensitive data in frago’s encrypted vault and reference them in your Recipe using `{{ env.VAR_NAME }}`.","tip":"Test your Recipe in `DEV` mode first with `frago run simulate --recipe your_recipe.yaml` to catch issues early."},{"step":"Execute the Recipe using frago’s CLI. For browser automation, ensure Chrome/Edge is installed and the CDP port is accessible. Monitor progress with `frago run watch --id {run_id}`.","tip":"For long-running workflows, use `frago run daemon --recipe your_recipe.yaml` to run in the background."},{"step":"Retrieve and process outputs from the persistent Run context. Use `frago run get-context` to fetch data or `frago run export --format csv` to download results for further analysis.","tip":"Combine frago with tools like Airflow or Prefect to orchestrate multiple Recipes into larger pipelines."},{"step":"Iterate based on outputs. If errors occur, review screenshots (for browser steps) or logs (`frago run get-logs --id {run_id}`) to refine your Recipe.","tip":"Enable frago’s analytics dashboard to track Recipe performance and identify bottlenecks over time."}]

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/tsaijamey/frago

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Design a multi-runtime automation workflow for [TASK] using frago's Recipe system. Include: 1) A metadata-driven Recipe that chains [STEP_1], [STEP_2], and [STEP_3] with error handling for [ERROR_CONDITION]. 2) A persistent Run context to store outputs from each step. 3) Native CDP browser control for [BROWSER_ACTION] in Step 2. Use frago's CLI to execute the Recipe and monitor the Run context in real-time.

Example Output

Here’s a production-ready frago Recipe for automating competitor pricing analysis across 3 e-commerce sites. The workflow includes:

**Recipe Metadata:**
```yaml
name: competitor_price_tracker
version: 1.0.0
steps:
  - id: fetch_sitemap
    action: frago.http.get
    input:
      url: "https://{competitor_domain}/sitemap.xml"
      headers:
        User-Agent: "Mozilla/5.0 (frago-agent/1.0)"
    output: sitemap_data
    error_handler:
      retry: 3
      on_failure: notify_ops_team

  - id: scrape_product_pages
    action: frago.browser.navigate
    input:
      url: "{{ steps.fetch_sitemap.outputs.sitemap_data.urls.product }}"
      cdp_commands:
        - "Page.navigate"
        - "Runtime.evaluate"
    output: product_data
    error_handler:
      screenshot: true
      on_failure: log_error_and_continue

  - id: compare_prices
    action: frago.data.compare
    input:
      reference_data: "{{ steps.scrape_product_pages.outputs.product_data }}"
      threshold: 0.15
    output: price_alerts
```

**Persistent Run Context:**
- The Recipe stores outputs in frago’s Run context (`frago run get-context --id {run_id}`), including:
  - Raw HTML from Step 1
  - Screenshots of failed pages (Step 2)
  - JSON array of price alerts (Step 3)

**Execution & Monitoring:**
```bash
# Start the workflow
frago run execute --recipe competitor_price_tracker.yaml --env PROD

# Monitor in real-time
frago run watch --id {run_id} --output json

# Retrieve results
frago run get-context --id {run_id} | jq '.price_alerts[] | select(.severity == "high")'
```

**Output:**
```json
{
  "price_alerts": [
    {
      "product_id": "SKU-12345",
      "competitor": "AcmeCorp",
      "our_price": 99.99,
      "competitor_price": 84.99,
      "savings_pct": 15.01,
      "severity": "high",
      "screenshot_url": "s3://frago-runs/{run_id}/screenshots/SKU-12345.png"
    }
  ]
}
```

**Key Features Demonstrated:**
1. **Metadata-Driven:** The Recipe is defined in YAML with explicit steps, inputs, and error handling.
2. **Multi-Runtime:** Combines HTTP requests (Step 1), CDP browser control (Step 2), and data comparison (Step 3).
3. **Persistent Context:** All outputs are stored for auditing or downstream processing.
4. **Error Resilience:** Failed steps trigger retries or notifications without halting the entire workflow.