A hook that stops Claude Code from re-trying fixes that failed
Hard-blocks AI agents from re-applying failed fixes across session restarts.
A completion-claim gate for Claude Code. Refuses to let the agent say done without evidence.
Stop hook enforcement beats trusting agents to self-verify their work.
Developers using Claude Code for autonomous tasks
Hard-blocks AI agents from re-applying failed fixes across session restarts.
Blocks Git pushes until you do pushups—clever gimmick, zero staying power.
Markdown based idea queue with Stop hooks for Claude Code sessions.
Claude Code safety gate that blocks breaking changes; solves real foot-gun but limited to one AI tool.
Three-layer orphan process cleanup for Claude Code's known memory leak.
Haiku classifier distinguishes blocking questions from closing pleasantries — clever workaround.