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.
git clone --depth 1 https://github.com/obviousworks/vibe-coding-ai-rulesWrote 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/obviousworks/vibe-coding-ai-rules/002-security)<a href="https://agentmods.dev/rules/obviousworks/vibe-coding-ai-rules/002-security"><img src="https://agentmods.dev/badge/rules/obviousworks/vibe-coding-ai-rules/002-security/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.
<a href="https://agentmods.dev/rules/obviousworks/vibe-coding-ai-rules/002-security"><img src="https://agentmods.dev/badge/rules/obviousworks/vibe-coding-ai-rules/002-security.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00253 | $0.00253 |
| Opus 5.5 | $0.00101 | $0.00101 |
| Sonnet 5.5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
002-security 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 1mo 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.
What it actually says
Security Rules
Core Principles
- All AI-generated code requires human security review
- Trust nothing, verify everything
- Defense in depth: multiple security layers
- Principle of least privilege
Input Validation (MANDATORY)
- Validate ALL user input with schema validation (Zod, Pydantic, etc.)
- Never trust client-side data
- Sanitize HTML content before rendering
- Validate file uploads: MIME type, extension, max size
Injection Prevention
- NEVER concatenate SQL strings — use parameterized queries
- NEVER pass user input to shell commands
- NEVER use dangerouslySetInnerHTML without DOMPurify
- NEVER use eval() or Function() with user input
Authentication & Secrets
- Never store secrets in source code or client-side code
- Use environment variables for all credentials
- Implement proper JWT validation with algorithm pinning
- Use httpOnly, secure, sameSite cookies
API Security
- Rate limiting on all endpoints
- CORS configuration: explicit origins only
- Input size limits on all endpoints
- Proper HTTP security headers (CSP, HSTS, etc.)
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.
- 1mo ago First seen · 38 lines · 253 tokens per session scan A 60d03f302181
002-security is a cursor rule published in the GitHub repository obviousworks/vibe-coding-ai-rules (93 stars, last pushed 4mo ago), licensed MIT. It adds 253 tokens to every session, about $0.0010 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
tools
(none|read|write|network|exec) and risk (low|medium|high|critical). These drive the permission classifier — be honest.
react
React best practices and patterns for modern web applications.
remote-pc
Drive a host running agentic-remote-pc over its MCP runner. Use when the user asks to run commands on a remote PC, drive a coding-agent CLI on a host, or validate a local feature/deployment.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.