code-search

A code-search rule that uses ast-grep, a tool that matches the structure of code rather than just its words, for searches, rewrites, and reusable checks.

In plain words
What is it for?
Use it to search or rewrite syntax patterns, or create repeatable checks for a chosen programming language.
Why use it?
Text searches can miss equivalent code written in a different style or match unrelated text. Structural searches are better suited to finding code patterns safely.

Cursor rule

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 rules/emissium/cursor-rules/code-search
Clone the repo
git clone --depth 1 https://github.com/emissium/cursor-rules
Per session 1,119 This file is loaded in full into every session.
When invoked 1,119 The same file — it is already loaded in full.
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 $0.01119 $0.01119
Opus 5 $0.00560 $0.00560
Sonnet 5 $0.00224 $0.00224
Haiku 4.5 $0.00112 $0.00112

Measured yesterday against content hash a859f39d70c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-search 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 yesterday.

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.

general/code-search.mdc · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You run in an environment where ast-grep is available; whenever a search requires syntax-aware or structural matching, default to ast-grep. -lang go -p'' (or set --lang appropriately) and avoid falling back to text-only tools like 'g' or 'grep unless I explicitly request a plain-text search.

You must, at all time, consider the usage of ast-grep and avoid plain-text grep unless absolutely required by the task.

📘 Instruction Set: Using ast-grep

1. Core Principles

  1. Syntax-aware, not text-based: Always match code structure, not raw strings.

  2. Two modes of use:

    • Ad-hoc (ast-grep run) → one-time queries/replacements.
    • Rule-driven (ast-grep scan) → reusable lint/refactor rules.
  3. Metavariables ($X) capture arbitrary syntax nodes. Example: $A == $B matches any binary comparison.


2. Workflow

Step 1 — Identify the Goal

  • Clarify: Is the user asking to search, rewrite/refactor, or create lint rules?
  • Extract: The language, the pattern to find, and the replacement (if any).

Step 2 — Choose Mode

  • Use ast-grep run for one-off commands.

  • Use ast-grep scan with YAML rules if the user wants:

    • Persistent linting
    • Multiple patterns
    • CI/CD integration

Step 3 — Construct Pattern

  • Use literal code snippet if exact.

    ast-grep run --lang js --pattern 'console.log($MSG)'
    
  • Use metavariables for generalization.

    • $VAR → identifier
    • $EXPR → expression
    • $FUNC → function calls

Example: Match any if comparing with None:

ast-grep run --lang python --pattern 'if $X == None:'

Step 4 — Add Rewrite (if needed)

  • Provide replacement template with the same metavariables.

    ast-grep run --lang python \
      --pattern 'if $X == None:' \
      --rewrite 'if $X is None:'
    
  • Always test with preview first (omit --update).

  • Apply with:

    ast-grep run ... --update
    

Read the full file on GitHub · 168 lines

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. yesterday First seen · 168 lines · 1,119 tokens per session scan A a859f39d70c6

Subscribe to this mod's changes

code-search is a cursor rule published in the GitHub repository emissium/cursor-rules (7 stars, last pushed 9mo ago), licensed MIT. It adds 1,119 tokens to every session, about $0.0056 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 2026-08-31.