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.
npx agentmods add rules/pralhadyadawad/avvarre/cursorrulesgit clone --depth 1 https://github.com/PralhadYadawad/avvarreWrote 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.
[](https://agentmods.dev/rules/pralhadyadawad/avvarre/cursorrules)<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>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.
| Model | Per session | Once 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 |
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.
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 |
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.
- 3d ago First seen · 57 lines · 1,041 tokens per session scan A 9e64fb0853d3
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.
Other cursor rules, from other repositories
graphql
GraphQL: schema design, resolvers, performance.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.