code review gate
by Yashwanth Thota
Confidence-scored code review that flags AI-slop patterns, plus a finish-line gate: tests, review, bounded fix loop, commit-ready summary.
by Yashwanth Thota
Confidence-scored code review that flags AI-slop patterns, plus a finish-line gate: tests, review, bounded fix loop, commit-ready summary.
by Yashwanth Thota
One-shot LLM calls from scripts and hooks via headless claude -p, with a recursion guard, JSON envelope parsing, tool restriction and spend logging.
by Yashwanth Thota
Local hybrid keyword + semantic code search for agents: SQLite FTS5 BM25 plus optional embeddings, as a CLI and an MCP server.
by Yashwanth Thota
Per-model and per-session Claude Code usage report from your local transcripts, with interactive and background claude -p calls split out.
by Yashwanth Thota
Hooks that save changed files, open todos and recent commands before Claude Code compacts, then re-inject them afterwards.
by Yashwanth Thota
Shared scratchpad memory for parallel Claude Code agents and subagents: CLI, MCP server and optional hooks, local SQLite.
by Yashwanth Thota
Write Conventional Commits messages from staged diffs: type, scope, imperative summary, why-focused body, breaking-change footers.
by Yashwanth Thota
Speak terminal and agent output aloud on macOS. Voice and speed follow the text's tone (success, error, calm). Local TTS, optional Haiku tone detection.