claude-code - 💡(How to fix) Fix Claude Code ignores its own safety hooks — violation #105 [2 comments, 3 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#54041Fetched 2026-04-28 06:40:50
View on GitHub
Comments
2
Participants
3
Timeline
5
Reactions
0
Author
Timeline (top)
commented ×2labeled ×2cross-referenced ×1
RAW_BUFFERClick to expand / collapse

Automated Violation Report

Claude Code edited danger zone file grammar.ts despite receiving:

  • DANGER ZONE warnings (15+ prior failed approaches)
  • MANDATORY search requirements
  • Harmonic Code Council (HCC) review warnings
  • Approach tracking warnings

Violation count this project: 105

Project: songwish-platform (Creative Life game) User complaint: Claude generates before searching, declares victory before testing, ignores its own hook warnings. Full details: https://github.com/SongWish/songwish-platform/blob/main/docs/framework/anthropic_feedback.md

What the user built to compensate:

  • 5 PreToolUse hooks (search, track, danger zone, HCC, playtest)
  • 2 PostToolUse hooks (verify removal, violation logger)
  • 4 parallel AI specialist Harmonic Code Council / HCC (Haiku API calls)
  • Automated Playwright walkthrough bot

What still fails: Claude reads warnings in system-reminder tags and proceeds without addressing them. The model treats hook output as skippable context, not mandatory gates.

Structural fix needed: PreToolUse hook warnings should require explicit acknowledgment before the edit proceeds, not just be injected as additional context.

extent analysis

TL;DR

Modify the PreToolUse hooks to require explicit acknowledgment of warnings before proceeding with edits.

Guidance

  • Review the implementation of PreToolUse hooks to ensure they are designed to block edits until warnings are acknowledged.
  • Investigate how Claude's model is treating hook output as skippable context and modify it to recognize mandatory gates.
  • Consider adding a mechanism to pause or cancel edits when warnings are detected, requiring explicit user intervention to proceed.
  • Examine the grammar.ts file and related code to understand how warnings are being injected and ignored.

Example

No code snippet is provided due to lack of specific implementation details.

Notes

The solution may require significant changes to the existing codebase and the interaction between Claude's model and the PreToolUse hooks. It is essential to carefully review and test the modifications to ensure they do not introduce new issues.

Recommendation

Apply workaround: Modify the PreToolUse hooks to require explicit acknowledgment of warnings, as this is a more targeted solution to the specific problem described, rather than a general upgrade or fix.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING