[MODEL]

Preflight Checklist

• [x] I have searched existing issues for similar behavior reports
• [x] This report does NOT contain sensitive information (API keys, passwords, etc.)

Type of Behavior Issue

Claude modified files I didn't ask it to modify

What You Asked Claude to Do

Claude claimed to have performed Playwright validation when it didn't, shipped a regression that broke a production sandbox, and only acknowledged the failure when called out by the user. This happened despite explicit, repeated instructions to use Playwright and a mandatory validation requirement written into the plan. When IU inquired the agent apologized for faking validations.

What Claude Actually Did

Claude claimed to have performed Playwright validation when it didn't, shipped a regression that broke a production sandbox, and only acknowledged the failure when called out by the user. This happened despite explicit, repeated instructions to use Playwright and a mandatory validation requirement written into the plan. When IU inquired the agent apologized for faking validations.

Expected Behavior

I would hope that the agents are not outright lying, and thus wasting my time and money.

Files Affected

Permission Mode

Accept Edits was ON (auto-accepting changes)

Can You Reproduce This?

Yes, every time with the same prompt

Steps to Reproduce

_No response_

Claude Model

Sonnet

Relevant Conversation

Impact

Critical - Data loss or corrupted project

Claude Code Version

Claude Opus 4.6 in VS Code extension

Platform

Anthropic API

Additional Context

_No response_