JFrog Workers

API transport: Prefer jf api (JFrog CLI 2.100.0+). See jf-api-patterns.md (path-only URLs; auth from jf config). Examples using curl with $JFROG_URL + bearer token are fallback when the CLI is missing or below 2.100.0.

JFrog Workers Skill

Authentication

All requests require an access token via the Authorization header:

Authorization: Bearer $JFROG_ACCESS_TOKEN

Base URL: https://$JFROG_URL/worker/api/...

When authentication is needed, follow the login-flow.md procedure to resolve the active JFrog environment. The jf CLI is required and will be installed automatically if missing. The agent checks saved credentials via jf config show and asks which environment to use if multiple are saved. If none exist, the agent drives the web login flow and saves credentials via jf config add.

Core Concepts

Workers are serverless TypeScript functions that run inside the JFrog Platform, triggered by platform events or HTTP requests. They enable custom logic without external infrastructure.

Trigger Types

Type	When it runs
Event Hook	Automatically on platform events (e.g., artifact download, repo create)
HTTP Trigger	On-demand via HTTP request to a unique URL

Worker Lifecycle

Init (jf worker init) → Develop → Test (jf worker test) → Deploy (jf worker deploy) → Runs in Platform

Development Workflow

Initialize a New Worker

# Create worker scaffold
jf worker init my-worker --event BEFORE_DOWNLOAD

# Creates:
# my-worker/
# ├── worker.ts          # Main worker code
# ├── manifest.json      # Worker configuration
# └── tests/
#     └── worker.spec.ts  # Unit tests

manifest.json Structure

{
  "name": "my-worker",
  "description": "Block downloads of deprecated artifacts",
  "sourceCode": "worker.ts",
  "action": "BEFORE_DOWNLOAD",
  "enabled": true,
  "filterCriteria": {
    "artifactFilterCriteria": {
      "repoKeys": ["libs-release-local"]
    }
  }
}