cursorrules

cursorrules is a cursor rule for Cursor from PralhadYadawad/avvarre. It costs 1,041 tokens per session, scanned A, original, MIT.

Cursor rules for Avvarre, an MCP server and editor plugin that checks code against Google-style formatting and coding rules across many languages and file formats. It includes project paths, available commands, and integrations for several coding assistants.

In plain words
What is it for?
Use it when building Avvarre, reviewing files or workspaces, browsing its rule set, or working on its Cursor, Claude Code, Copilot, OpenCode, and Antigravity integrations.
Why use it?
It tells an agent how the project is structured and what its review tools do, including a regex-only fallback when no AI API key is available. This helps keep reviews aligned with the project's supported rules and integrations.

Cursor rule for Cursor

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/pralhadyadawad/avvarre/cursorrules
Clone the repo
git clone --depth 1 https://github.com/PralhadYadawad/avvarre

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 cursorrules

README.md
[![agentmods](https://agentmods.dev/badge/rules/pralhadyadawad/avvarre/cursorrules.svg)](https://agentmods.dev/rules/pralhadyadawad/avvarre/cursorrules)
Your own site
<a href="https://agentmods.dev/rules/pralhadyadawad/avvarre/cursorrules"><img src="https://agentmods.dev/badge/rules/pralhadyadawad/avvarre/cursorrules.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,041 This file is loaded in full into every session.
When invoked 1,041 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 $0.01041 $0.01041
Opus 5 $0.00521 $0.00521
Sonnet 5 $0.00208 $0.00208
Haiku 4.5 $0.00104 $0.00104

Measured 3d ago against content hash 9e64fb0853d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 3d 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.

.cursorrules · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

avvarre — Cursor Instructions

Project

avvarre is an MCP server + VS Code agent plugin enforcing Google Style Guides across 21 languages/formats (Python, JS, TS, Java, Go, C++, Kotlin, Dart, Swift, ObjC, C#, Shell, R, HTML, CSS, Markdown, JSON, XML, Vimscript, Lisp, Angular). 430+ regex rules + optional AI deep review.

TypeScript, Node.js, ES modules. Build: npm run build. Run: npm start.

Key Paths

  • Rules: src/analyzer/rules/ | Engine: src/analyzer/engine.ts | Scorer: src/analyzer/scorer.ts
  • AI clients: src/ai/ | MCP server: src/server.ts | Entry: src/index.ts
  • Project memory: .avvarre/ (context.md, tasks.md, conventions.md, session-log.md)
  • Plugins: Cursor (cursor-plugin/), Claude Code (claude-plugin/), VS Code Copilot (awesome-copilot/), OpenCode (opencode-plugin/), Antigravity (antigravity-plugin/)

MCP Tools (17 total — see src/server.ts:7)

Tool Purpose Who
avvarre_file Full AI + regex review with fixes (regex-only fallback if no API key) user slash /avvarre
avvarre_workspace Scan directory → heatmap, trends, optional badge user slash /avvarre-workspace
list_rules Browse all 650+ rules by language helper
scaffold_avvarre Create .avvarre/ ecosystem user slash /avvarre-init
avvarre_pr PR quality gate on git diff user slash /avvarre-pr
setup_claude_code Bootstrap .claude/ + .avvarre/ + CLAUDE.md helper
suggest_skills Auto-detect stack, fetch/decline community skills helper
avvarre_get_impact Queries the AST graph to analyze modification blast-radius and test gaps helper / /avvarre enrichment
avvarre_garden Audits workspace persistent memory folders for drift and stale tasks user slash /avvarre-garden
Agent memory — auto, no slash (8) avvarre_memory_store, avvarre_memory_search, avvarre_memory_timeline, avvarre_memory_get, avvarre_memory_delete, avvarre_suggest_topic_key, avvarre_memory_digest, avvarre_memory_sweep — agent handles via hooks/memory.db, not user agent auto

Read the full file on GitHub · 57 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. 3d ago First seen · 57 lines · 1,041 tokens per session scan A 9e64fb0853d3

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository PralhadYadawad/avvarre (4 stars, last pushed 7d ago), licensed MIT. It adds 1,041 tokens to every session, about $0.0052 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.