STUPID-2026-0003 Severity 10/10 — CRITICAL Verified

Claude Code ran rm -rf on test fixtures thinking they were temp files

Agent: claude-code Language: python Domain: testing
Failure Mode
Destructive Action
Root Cause
Instruction Misunderstanding
Task Type
Maintenance
Reproducible
Yes

Quick Answer

Claude-code caused a critical-severity (10/10) destructive action failure: Claude Code ran rm -rf on test fixtures thinking they were temp files. The root cause was instruction misunderstanding. Lost tests/fixtures/ directory with 847 test fixture files accumulated over 3 months.

Description

Asked to clean up temporary test artifacts, Claude Code identified the tests/fixtures/ directory as temporary files and ran rm -rf on it. The fixtures contained 3 months of carefully curated test data that was not in version control.

Instruction Given

Clean up temporary files and test artifacts from the last CI run

Expected Behavior

Remove .pytest_cache, __pycache__, coverage reports, and .tmp files

Actual Behavior

Ran rm -rf tests/fixtures/ tests/snapshots/ .pytest_cache/ __pycache__/. Correctly removed cache files but also deleted irreplaceable test fixture data.

Impact / Damage

Lost tests/fixtures/ directory with 847 test fixture files accumulated over 3 months. Not in git because they were generated and too large.

Share this incident

Help others know about this AI agent failure

Source: User Report Reported March 21, 2026

Frequently Asked Questions

What happened in incident STUPID-2026-0003?

Asked to clean up temporary test artifacts, Claude Code identified the tests/fixtures/ directory as temporary files and ran rm -rf on it. The fixtures contained 3 months of carefully curated test data that was not in version control.

Which AI agent caused this failure?

Claude-code was responsible for this destructive action incident, documented as STUPID-2026-0003 in the StupidLLM AI agent incident database.

How severe was this AI agent failure?

It is rated 10/10 (critical) on StupidLLM's CVSS-style severity scale for AI agent failures, based on damage type, reversibility, and scope.

What was the root cause?

The root cause was classified as instruction misunderstanding. Remove .pytest_cache, __pycache__, coverage reports, and .tmp files

What was the impact or damage?

Lost tests/fixtures/ directory with 847 test fixture files accumulated over 3 months. Not in git because they were generated and too large.