Ast Grep — Testing skill for Claude Code
This command helps to create and test ast-grep rules for code quality enforcement.
How to install Ast Grep
Installs to ~/.claude/commands/neondatabase-claude_astgrep-ast_grep.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/neondatabase/claude_astgrep/HEAD/.claude/commands/ast_grep.md -o ~/.claude/commands/neondatabase-claude_astgrep-ast_grep.md Restart Claude Code, or start a new session, for it to be picked up.
What Ast Grep does
allowed-tools: Bash(ast-grep:*), Bash(uv run ast-grep:*), WebFetch(domain:ast-grep.github.io) description: This command helps to create and test ast-grep rules for code quality enforcement.
Recall the following ast-grep rules. You will need them for the next task. If this guideline misses something, read the web (e.g. https://ast-grep.github.io/reference/rule.html)
ast-grep YAML Rule Writing Guide
Core Concepts
ast-grep operates on Concrete Syntax Trees using Tree-sitter parser
Alternatives in Testing
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- Deslop Reborn — One iteration of the IronClaw Reborn de-slop loop — take ONE Reborn crate, fan out parallel review sub-agents 12.6k ★
- Deliver — Delivery phase - Review, validate, and test with multi-AI quality assurance 2.8k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claude Codepro
by Max Ritter - Professional development environment for Claude Code with spec-driven workflow, TDD enforcemen
Environment Setup
Dependency doctor for the simpleharness harness — checks pwsh / gh / ripgrep / ast-grep / python / node, insta
Fia Harness
Local, dependency-free spec-driven development harness for AI agents: spec-first, machine-validated state and
AI Engineering Framework
Spec-first AI-engineering framework for Claude Code: lifecycle skills, reviewer subagents, and CI-enforced qua
Root Cause Fix
Root-cause-first TDD loop for any bug or data fix. Forces a failing reproduction test BEFORE touching producti
Agentgovbench
48-scenario benchmark testing identity, policy enforcement, and observability across AI agent runtimes.
Related Agents
Ast Grep Surgeon
Structural code analysis and surgical refactoring specialist using ast-grep. Use PROACTIVELY for code search,
Parser Expert
Lark grammar and parser expert. Use when adding new MIDI commands, modifying grammar rules, working with AST t
Task Researcher
작업 구현 리서치 전문가. /task-start 스킬 시작 시 CLAUDE.md·INDEX.md·RULES.md를 스캔해 필요한 지침만 선별 로드하고, grep/LSP로 대상 파일·심볼·의존 관계를