lazyants/claude-plugins

Opt out of telemetry across every locally installed AI CLI and AI-enabled IDE, plus macOS/Windows OS-level privacy surfaces.

Personalized, behavior-aware analysis of where your Claude Code (Max/Pro) usage-limit tokens go, with ranked, low-effort ways to use fewer — computed entirely from your local session logs. Python measures; Claude concludes.

Stop AI coding agents from accidentally emptying your database. An always-on hook blocks destructive DB commands across 15+ frameworks, plus a stack-aware installer for database-level privilege separation and framework boot guards.

Generate and maintain a Diátaxis-structured end-user handbook for any project from a per-project profile, with live screenshot capture and ongoing completeness audits; ships Obsidian-vault and static-Markdown publish adapters.

High-fidelity literary book translation from a Gutenberg EPUB source (expert-mode `custom` extractor also supported), run to convergence through a codex-translate -> false-green gate -> codex-review -> Claude-fix loop over a frozen name/realia canon, with configurable verse policy, ledger resumability, and optional assembly into a rendered Obsidian glossary-wiki.

Understand and diagnose Claude Code plugin behavior across multiple CLAUDE_CONFIG_DIR profiles. Explains why profiles that share a plugins store hit recurring "corrupted installLocation" errors and cross-profile plugin deletion, ships a read-only health-check script that detects shared registries and cross-profile pointer leaks, and documents the reverse-engineered CLI validation and garbage-collection mechanism behind it.

Set up, migrate, audit, and operate an Obsidian vault as an LLM Wiki — a persistent, compounding knowledge base maintained by Claude Code.