Claude Code hook
Go Claude Code Comment Checker
Multi-language comment detection hook for Claude Code. 100% vibe coded by Claude Opus 4.5.
Install
brew install comment-checkerFound in the project README. Check it for setup steps after installing.
git clone https://github.com/code-yeongyu/go-claude-code-comment-checker.gitFrom the README
comment-checker 100% vibe coded. zero comments in my code, zero comments in yours. this entire repo - code, docs, readme, everything - was written by LLMs. shoutout to claude opus 4.5. A PostToolUse hook for Claude Code / OpenCode that yells at you when you write unnecessary comments. Built with Rust + tree-sitter. Fast. Opinionated. No mercy. why comments are code smell. if your code needs comments to be understood, your code sucks. this hook watches every Write, Edit, MultiEdit and screams when it detects comments. exceptions exist. BDD comments (# given, # when, # then), linter directives (# noqa, // @ts-ignore), shebangs - these are fine. everything else? delete it. yes, even docstrings. install npm / bun homebrew (macos/linux) manual grab binary from releases. setup add to ~/.claude/settings.json (or .claude/settings.json in your project): done. now claude will think twice before leaving // TODO: fix later in your code. what it catches what it allows 30+ languages python, go, typescript, javascript, rust, c, c++, java, ruby, php, swift, kotlin, scala, elixir, and more. if tree-sitter supports it, we support it. the archived Go implementation lives under go/; the production CLI is Rust. how it works 1. hook receives JSON from Claude Code 2. extracts content from Write/Edit/MultiEdit tool input 3. detects language from file extension 4. parses AST with tree-sitter 5. finds comment nodes 6. filters out allowed patterns (BDD, directives, shebangs) 7. if anything remains → exit 2 with warning message the Rust workspace also has buildable wasm32-unknown-unknown and N-API binding crates for future consumers. those paths are CI buildability gates for now; npm still ships native binaries. exit codes custom prompt you can replace the default warning…
How hooks work
- Hooks are shell commands Claude Code runs at fixed points: before or after a tool call, when you submit a prompt, when Claude stops, on notifications and at session start.
- They are set in the hooks section of ~/.claude/settings.json (or .claude/settings.json for a project), or come bundled in a plugin.
- A hook can block a tool call, add context, or run a formatter or test. Read the scripts before you install them: they run on your machine with your permissions.
Details
- Repository
- code-yeongyu/go-claude-code-comment-checker
- Type
- Hooks
- Language
- Go
- License
- MIT
- Last updated
- 30 September 2026
FAQ
What is Go Claude Code Comment Checker?
Multi-language comment detection hook for Claude Code. 100% vibe coded by Claude Opus 4.5. It is a hook for Claude Code, from code-yeongyu/go-claude-code-comment-checker on GitHub.
How do I install Go Claude Code Comment Checker?
Run brew install comment-checker, then follow the setup in the README.
Is Go Claude Code Comment Checker popular?
code-yeongyu/go-claude-code-comment-checker has 25 GitHub stars and 8 forks. It was last updated on 30 September 2026.
More hooks
Claude Config Editor
26jung-wan-kim/claude-config-editor
Visual Config Editor for Claude Code - Drag & Drop Hook Pipeline, Agent Workflow, Skill/Rule Editor
Claude Mem Sync
27lopadova/claude-mem-sync
Team memory sharing for claude-mem — sync AI memories across developers, with Claude Code plugin, github action and knowledge distillation
Hatch3r
26hatch3r/hatch3r
Open-source CLI + editor plugin (Claude Code, Cursor, GitHub Copilot): one command installs 29 agents, 53 skills, 67 rules, 30 commands, 7 hooks & MCP integrations into any repo. Audited each release across 24 governance domains.
Claude Skills
27randommonicle/claude-skills
Engineering guardrails for Claude Code: 51 skills, reviewer agents and hooks, most written after a real defect shipped. Installable as a plugin.
Hardstop
32frmoretto/hardstop
Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era.
Agentic Tools
26acedergren/agentic-tools
Comprehensive toolkit for AI-assisted development: Claude Code permissions (400+ tools), Git workflows, and automation hooks
Browse the most popular Claude Code mods, all hooks, or the skills and MCP server directories.