ast-grep
Structural code search via ast-grep — use when code shape and element relationships matter, not just text. E.g., "find async functions without error handling", "refactor foo(a, b) to foo({ a, b })". Use Grep for simple name lookups.
- Installs
- 232
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/poteto/noodle --skill ast-grep- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads ast-grep automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
ast-grep
Workflow
- Write a test snippet representing the target code
- Write the rule (start with
pattern, escalate tokind+has/insideif needed) - Test with
--stdinbefore searching the codebase - Search the codebase once the rule matches
Critical Gotchas
Always use stopBy: end on relational rules
Without it, has/inside stop at the first non-matching node instead of traversing the full subtree:
# WRONG — will miss deeply nested matches
has:
pattern: await $EXPR
# RIGHT
has:
pattern: await $EXPR
stopBy: end
Escape metavariables in shell
$VAR gets interpreted by the shell. Either escape or single-quote:
# Double-quoted: escape with backslash
ast-grep scan --inline-rules "id: test
language: javascript
rule:
pattern: await \$EXPR" .
# Single-quoted: no escaping needed
ast-grep scan --inline-rules 'id: test
language: javascript
rule:
pattern: await $EXPR' .
Metavariables must be the sole content of an AST node
These don't work: obj.on$EVENT, "Hello $WORLD", a $OP b, $jq
Use $$OP for unnamed nodes (operators, punctuation). Use $$$ARGS for zero-or-more nodes.
Testing with --stdin
echo "async function test() { await fetch(); }" | ast-grep scan --inline-rules 'id: test
language: javascript
rule:
kind: function_declaration
has:
pattern: await $EXPR
stopBy: end' --stdin
Debugging with --debug-query
When rules don't match, inspect the AST to find correct kind values:
ast-grep run --pattern 'your code here' --lang javascript --debug-query=cst
Formats: cst (all nodes), ast (named only), pattern (how ast-grep sees your pattern).
Rule syntax
See references/rule_reference.md for the full rule reference (atomic, relational, composite rules, and metavariables).
FAQ
What does the ast-grep skill do?
Structural code search via ast-grep — use when code shape and element relationships matter, not just text. E.g., "find async functions without error handling", "refactor foo(a, b) to foo({ a, b })". Use Grep for simple name lookups.
How do I install ast-grep?
Run npx skills add https://github.com/poteto/noodle --skill ast-grep in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/ast-grep/ (personal) or .claude/skills/ast-grep/ (project).
Which AI agents can use ast-grep?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is ast-grep safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains ast-grep?
It is published by poteto in poteto/noodle. It has 232 recorded installs.
More from poteto/noodle
adversarial-review
poteto/noodle
Adversarial code review using cross-model approach. Spawns reviewers on the opposing model (Claude uses Codex, Codex uses Claude) to challenge work from distinct critical lenses. Produces a synthesized verdict with findings and lead judgment. Triggers: "adversarial review".
unslop
poteto/noodle
Remove AI writing patterns from prose. Use for docs, READMEs, blog posts, any non-code text that should sound human. Triggers: "unslop", "humanize", "make this sound human", "clean up this writing", "edit for voice", "de-AI this text".
ts-best-practices
poteto/noodle
Open the skill to read its SKILL.md instructions.
debugging
poteto/noodle
Systematic root-cause debugging methodology. Use for any technical problem — errors, failures, unexpected behavior, or when stuck. Triggers: "debug", "fix this", "what's wrong", "investigate".
quality
poteto/noodle
Post-cook quality gate. Reviews completed cook work for correctness, scope discipline, and principle compliance. Emits stagemessage events with findings. Triggers after execute stages, on '/quality', 'review this', 'check the work', 'assess quality'.
commit
poteto/noodle
Create conventional commit messages. Use when the user says "commit this", "save changes", "git commit", asks to commit code, write a commit message, or format git history. Follows conventional commits specification.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.