Sponsor Suno AI Music arrow_forward
Slash Command

Run Integration

Run integration test suites with proper setup and teardown

Type
Slash Command
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026

What Run Integration is

Run Integration is a slash command published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Run Integration gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Run Integration

Claude Code

  1. Download run-integration.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/testing/integration-test-runner/commands/run-integration.md, shared under the repository's MIT license. Read the full file on GitHub.

Run integration tests with comprehensive environment setup, database seeding, service orchestration, and cleanup.

Purpose

Execute integration tests that verify interactions between multiple system components:

  • API endpoints with database operations
  • Microservices communication
  • Third-party service integrations
  • Full request/response workflows
  • Database transactions and state changes

Pre-Test Setup

Before running integration tests, ensure:

  1. Environment Configuration
  • Check for test environment variables
  • Verify test database connections
  • Confirm test API keys/credentials
  • Validate service dependencies are available
  1. Database Preparation
  • Create/reset test database
  • Run migrations
  • Seed test data
  • Clear any existing test data
  1. Service Dependencies
  • Start required services (Redis, message queues, etc.)
  • Check service health endpoints
  • Initialize mock services if needed
  • Set up test containers (Docker/Testcontainers)
  1. State Management
  • Clear caches
  • Reset file system test directories
  • Initialize test state

Test Execution

Run integration tests with:

# Run all integration tests
/run-integration

# Run specific test suite
/run-integration api

# Run with specific environment
/run-integration --env staging

# Run with coverage
/run-integration --coverage

Execution Process

  1. Pre-flight checks
  • Validate environment configuration
  • Check database connectivity
  • Verify service availability
  • Confirm no conflicting processes
  1. Setup phase
  • Initialize test database
  • Seed required data
  • Start dependent services
  • Configure test environment
  1. Run tests
  • Execute test suites in order
  • Capture detailed logs
  • Report progress
  • Handle test failures gracefully
  1. Teardown phase
  • Clean up test data
  • Stop test services
  • Reset environment
  • Generate test reports

Test Organization

Structure integration tests by:

  • API routes - Endpoint-specific tests
  • User workflows - End-to-end user journeys
  • Service interactions - Cross-service communication
  • Data flows - Multi-step data processing

Reporting

Generate comprehensive reports with:

  • Test results (pass/fail counts)
  • Execution time per test
  • Failed test details with stack traces
  • Code coverage (if enabled)
  • Service logs for failures
  • Database state at failure points

Cleanup

After tests complete:

  • Drop test database or truncate tables
  • Stop test containers/services
  • Remove temporary files
  • Clear test caches
  • Reset environment variables

Best Practices Applied

  • Isolation - Tests don't depend on each other
  • Idempotency - Tests can run multiple times safely
  • Fast feedback - Fail fast on setup errors
  • Clear reporting - Easy to identify failures
  • Proper cleanup - No test pollution
  • Realistic data - Test data resembles production

Example Output

Integration Test Runner
=======================

Setup Phase:
 Database connection verified
 Test database created and migrated
 Test data seeded (50 users, 200 products)
 Redis cache cleared
 Services healthy: api, worker, notifications

Running Tests:
 API Authentication Tests (5/5 passed) - 2.3s
 User Management Tests (12/12 passed) - 5.1s
 Order Processing Tests (8/8 passed) - 8.7s
 Payment Integration Tests (3/4 passed) - 4.2s
  └─ test_refund_webhook_handling FAILED
 Notification Tests (6/6 passed) - 3.1s
…

Troubleshooting

Common issues:

  • Connection refused - Check service is running
  • Database errors - Verify migrations are current
  • Timeout errors - Increase test timeouts
  • Port conflicts - Ensure test ports are available
  • Permission errors - Check file/database permissions

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Run Integration?

Run Integration is a slash command for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Run integration test suites with proper setup and teardown

How do I install Run Integration in Claude Code?

Download run-integration.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Run Integration in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Run Integration safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.