Hook

Why it matters

CLAUDE.md is ingested as conversational user context after the system prompt, meaning the model treats instructions as non-binding advice. To reliably block dangerous behavior like leaking credentials, teams must replace markdown rules with deterministic PreToolUse hooks.

Why it matters

Grepathy parses local Claude Code transcripts via git hooks to extract undocumented agent decisions and saves them as Markdown files. This solves the 30-day retention limit of Claude transcripts, ensuring teammates and future agents understand the architecture.

Why it matters

Calling prompt submission directly inside Claude Code mod buttons or command hooks silently fails to trigger turns. Decoupling the user click into a variable queue flushed by a session clock solves the silent drop. This pattern ensures extensions trigger agent turns consistently.

Why it matters

Learnlance watches code written by Claude Code, Cursor, Codex, and Copilot to construct an interactive, local knowledge graph of learned engineering concepts. It runs via detached background processes with zero external dependencies.

Why it matters

A new Claude Code plugin and npm package uses fast probability scoring to prune stale tool calls and outputs instead of summarizing them. By keeping kept messages verbatim, it prevents lost paths, constraints, and syntax errors.

Why it matters

Vomit is an open-source local CLI tool designed to translate dense and verbose token streams from Claude 5 into readable English. By piping Claude's terminal output through a local model like GPT-OSS 20B, it keeps developer sessions uncluttered without external telemetry.