ast-grep

A guide to ast-grep, a tool that searches and rewrites code by understanding its structure instead of treating it as plain text.

In plain words
What is it for?
Use it to set up ast-grep, scan projects, author and test rules, inspect query matches, and preview structural code changes.
Why use it?
It provides a safer workflow for writing rules, debugging unexpected matches, and reviewing automated rewrites before applying them.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/vinhnx/vtcode/ast-grep
Any agent
npx skills add vinhnx/VTCode --skill ast-grep
Clone the repo
git clone --depth 1 https://github.com/vinhnx/VTCode

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 23,734 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.23734
Opus 5 $0.00012 $0.11867
Sonnet 5 $0.00005 $0.04747
Haiku 4.5 $0.00002 $0.02373

Measured 2d ago against content hash 8771519d9649, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ast-grep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

crates/codegen/vtcode-skills/src/skills/assets/samples/ast-grep/SKILL.md · 1,412 lines

How it starts

The opening of the file, as written. The whole thing — 1,412 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ast-Grep

Use this skill for ast-grep project setup, rule authoring, rule debugging, and CLI workflows that go beyond a single structural query.

Routing

  • Use exec_command for ast-grep queries, project scans, rule tests, debug output, and rewrite previews.
  • Use ast-grep scan for project rules and ast-grep test for rule tests.
  • Use ast-grep run --pattern=... --rewrite=... --json=compact --color=never for dry-run rewrite previews. Review every replacement before applying changes.
  • Use ast-grep run --debug-query when a query matches an unexpected syntax node.
  • Use --kind to match node kinds. Ast-grep supports ESQuery-style compound selectors and pseudo-selectors in supported releases.
  • Keep this skill read-only unless the user explicitly authorises applying a rewrite.

Quick Start

  • In VT Code, prefer vtcode dependencies install ast-grep before suggesting system package managers.
  • External install routes such as Homebrew, Cargo, npm, pip, MacPorts, or Nix are fallback options when the user explicitly wants a system-managed install.
  • After installation, validate availability with ast-grep --help.
  • On Linux, prefer the full ast-grep binary name over sg because sg may already refer to setgroups.
  • When running CLI patterns with shell metavariables like $PROP, use single quotes so the shell does not expand them before ast-grep sees the pattern.
  • A good first rewrite example is optional chaining, for example rewriting $PROP && $PROP() to $PROP?.().

Command Overview

  • ast-grep run: ad-hoc query execution and one-off rewrites.
  • ast-grep scan: project rule scanning.
  • ast-grep new: scaffold and rule generation.
  • ast-grep test: rule-test execution.
  • ast-grep lsp: editor integration via language server.

Built-In Languages

  • ast-grep ships many built-in languages. Common aliases include bash, c, cc / cpp, cs, css, ex, go / golang, html, java, js / javascript / jsx, json, kt, lua, md / markdown, php, py / python, rb, rs / rust, swift, ts / typescript, tsx, and yml.
  • --lang <alias> and YAML language: <alias> use those built-in aliases. File-system scans infer language from built-in extensions unless the project overrides them.
  • Pass --lang <alias> to the CLI when extension inference is insufficient.
  • Use languageGlobs when the repository needs a different extension mapping than ast-grep’s built-in defaults.

Read the full file on GitHub · 1,412 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 1,412 lines · 24 tokens per session scan A 8771519d9649

Subscribe to this mod's changes

ast-grep is a skill published in the GitHub repository vinhnx/VTCode (825 stars, last pushed 2d ago), licensed Apache-2.0. It adds 24 tokens to every session and 23,734 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

unifly

This skill should be used when the user asks to "manage UniFi devices", "configure UniFi networks", "create a VLAN", "provision an SSID", "create firewall rules", "reorder firewall policies", "create a NAT rule", "set up port forwarding", "configure masquerade NAT", "add DNS records", "manage traffic matching lists"…

hyperb1iss/unifly · 265 tokens

verify

Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.

zenbu-labs/terminal-browser · 37 tokens

claude-api

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…

warpdotdev/warp · 193 tokens

create-skill

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

warpdotdev/warp · 64 tokens

harbor

Run Terminal-Bench or any Harbor dataset with Ante as the agent, using the Harbor adapter in the ante repo's ante-harbor/ directory. Use when the user wants to benchmark Ante on Harbor or reproduce Ante's published eval results.

AntigmaLabs/ante · 51 tokens

gui-integration-test

GUI desktop app only. Writes, runs, and debugs Warp integration tests using the custom Builder/TestStep framework in crates/integration. Use when adding a new integration test, fixing a failing integration test, wiring a test into the manual runner or nextest suite, or verifying end-to-end UI and terminal behavior in…

warpdotdev/warp · 72 tokens