akanealw
eec8c28fb3
Some checks are pending
Go Benchmark / Performance Regression Check (push) Waiting to run
Cerberus Integration / Cerberus Security Stack Integration (push) Waiting to run
Upload Coverage to Codecov / Backend Codecov Upload (push) Waiting to run
Upload Coverage to Codecov / Frontend Codecov Upload (push) Waiting to run
CodeQL - Analyze / CodeQL analysis (go) (push) Waiting to run
CodeQL - Analyze / CodeQL analysis (javascript-typescript) (push) Waiting to run
CrowdSec Integration / CrowdSec Bouncer Integration (push) Waiting to run
Docker Build, Publish & Test / build-and-push (push) Waiting to run
Docker Build, Publish & Test / Security Scan PR Image (push) Blocked by required conditions
Quality Checks / Auth Route Protection Contract (push) Waiting to run
Quality Checks / Codecov Trigger/Comment Parity Guard (push) Waiting to run
Quality Checks / Backend (Go) (push) Waiting to run
Quality Checks / Frontend (React) (push) Waiting to run
Rate Limit integration / Rate Limiting Integration (push) Waiting to run
Security Scan (PR) / Trivy Binary Scan (push) Waiting to run
Supply Chain Verification (PR) / Verify Supply Chain (push) Waiting to run
WAF integration / Coraza WAF Integration (push) Waiting to run
949 B
Executable File
949 B
Executable File
mode, description, tools, model
| mode | description | tools | model | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| agent | Website exploration for testing using Playwright MCP |
|
Claude Sonnet 4 |
Website Exploration for Testing
Your goal is to explore the website and identify key functionalities.
Specific Instructions
- Navigate to the provided URL using the Playwright MCP Server. If no URL is provided, ask the user to provide one.
- Identify and interact with 3-5 core features or user flows.
- Document the user interactions, relevant UI elements (and their locators), and the expected outcomes.
- Close the browser context upon completion.
- Provide a concise summary of your findings.
- Propose and generate test cases based on the exploration.