ast-index

ast-index is a cursor rule for Cursor from defendend/Claude-ast-index-search. It costs 320 tokens per session, scanned A, original, MIT.

A set of project rules for using ast-index, a tool that searches code by its structure, such as symbols, classes, usages, and dependencies.

In plain words
What is it for?
Use it to find files, symbols, implementations, callers, outlines, module dependencies, project maps, and coding conventions. Fall back to text search for regular expressions, literal strings, comments, or missing indexed results.
Why use it?
It gives the coding agent a consistent way to navigate a codebase before falling back to broad text searches. It also explains how to prepare or rebuild the search index, including in monorepos, which are repositories containing multiple related projects.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it to find files, symbols, implementations, callers, outlines, module dependencies, project maps, and coding conventions. Fall back to text search for regular expressions, literal strings, comments, or missing indexed results.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/defendend/claude-ast-index-search/ast-index
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.

Clone the repo
git clone --depth 1 https://github.com/defendend/Claude-ast-index-search

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ast-index

README.md
[![agentmods](https://agentmods.dev/badge/rules/defendend/claude-ast-index-search/ast-index/github.svg)](https://agentmods.dev/rules/defendend/claude-ast-index-search/ast-index)
Your own site
<a href="https://agentmods.dev/rules/defendend/claude-ast-index-search/ast-index"><img src="https://agentmods.dev/badge/rules/defendend/claude-ast-index-search/ast-index/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ast-index

Your own site · 80×15
<a href="https://agentmods.dev/rules/defendend/claude-ast-index-search/ast-index"><img src="https://agentmods.dev/badge/rules/defendend/claude-ast-index-search/ast-index.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 320 This file is loaded in full into every session.
When invoked 320 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00320 $0.00320
Opus 5 $0.00160 $0.00160
Sonnet 5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured 11d ago against content hash df74aaf2d0fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ast-index 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 11d 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.

plugin/rules/ast-index.mdc · 40 lines

What it actually says

ast-index Search Rules

Use ast-index first for codebase navigation tasks: finding files, symbols, classes, usages, implementations, callers, outlines, module dependencies, and project maps.

Before the first query in a project, run ast-index stats. If there is no usable index yet, run ast-index rebuild from the project root. For large repositories, prefer a scoped rebuild with --include or work from the smallest relevant project root.

Do not run grep or broad text search after ast-index returns sufficient structural results. Fall back to text search only for regex searches, string literals, comments, or when ast-index returns no useful result.

Useful commands:

ast-index explore "how does X work"   # one-shot: ranked source + neighbours + tests (--rwr for graph)
ast-index search "Query"
ast-index file "FileName"
ast-index symbol "SymbolName"
ast-index class "ClassName"
ast-index usages "SymbolName"
ast-index implementations "InterfaceOrBaseClass"
ast-index refs "SymbolName"
ast-index outline "path/to/File.kt"
ast-index map --limit 20
ast-index conventions

For monorepos with a trusted parent index, use ast-index --walk-up ... or AST_INDEX_WALK_UP=1. Otherwise stay scoped to the nearest project root to avoid mixing unrelated results.

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. 11d ago First seen · 40 lines · 320 tokens per session scan A df74aaf2d0fc

Subscribe to this mod's changes

ast-index is a cursor rule published in the GitHub repository defendend/Claude-ast-index-search (560 stars, last pushed 5d ago), licensed MIT. It adds 320 tokens to every session, about $0.0016 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.