{"name":"waitdeadai-llm-dark-patterns","owner":{"name":"ClaudePluginHub"},"plugins":[{"name":"waitdeadai-llm-dark-patterns","source":{"source":"github","repo":"waitdeadai/llm-dark-patterns"},"description":"Out-of-band Claude Code Stop / SubagentStop hook judges that block 29 LLM dark patterns at the closeout boundary: false-success without evidence, sycophancy, paternalism, permission-loops, vibe time estimates, fake recall, fake stats, fake citations, context loss after compaction, multi-agent rollup failures, power-user polish failures, and unreachable new symbols (advisory). Deterministic verdicts, no network calls, no model in the verdict path, Apache-2.0, paper-grade claim ledger.","version":"1.0.0","strict":true,"keywords":["claude-code","hooks","dark-patterns","anti-sycophancy","anti-hallucination","verification","governance","ai-safety","llm-safety","abstention"],"category":"deployment"}]}