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/ofershap/vibe-guard/security-guardrailsgit clone --depth 1 https://github.com/ofershap/vibe-guardWrote 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/ofershap/vibe-guard/security-guardrails)<a href="https://agentmods.dev/rules/ofershap/vibe-guard/security-guardrails"><img src="https://agentmods.dev/badge/rules/ofershap/vibe-guard/security-guardrails.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 | $0.00282 | $0.00282 |
| Opus 5 | $0.00141 | $0.00141 |
| Sonnet 5 | $0.00056 | $0.00056 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
security-guardrails 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.
What it actually says
Before writing any code that handles user input, authentication, or database operations:
- NEVER hardcode API keys, passwords, tokens, or secrets - always use environment variables
- ALWAYS validate and sanitize user input before processing - use Zod, Joi, or equivalent
- ALWAYS add authentication middleware to API routes unless explicitly marked as public
- NEVER use string interpolation in SQL queries - always use parameterized queries
- ALWAYS set CORS to specific origins in production - never use wildcard (*)
- ALWAYS hash passwords with bcrypt/scrypt/Argon2 - never MD5, SHA1, or plain text
- ALWAYS set httpOnly, secure, and sameSite flags on cookies
- NEVER expose stack traces or internal errors to users in production
- ALWAYS add rate limiting to authentication endpoints
- NEVER commit .env files - always use .env.example with placeholder values
When generating a new API endpoint:
- Add input validation
- Add authentication check
- Add rate limiting for sensitive operations
- Return generic error messages
When generating database queries:
- Use parameterized queries or ORM methods
- Add Row-Level Security policies if using Supabase/Postgres
- Never trust user input in WHERE clauses
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 · 29 lines · 282 tokens per session scan A a9d39867ee27
security-guardrails is a cursor rule published in the GitHub repository ofershap/vibe-guard (1 stars, last pushed 6mo ago), licensed MIT. It adds 282 tokens to every session, about $0.0014 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
cursorrules
When building AI apps with this project, follow these conventions.
102-python-patterns
Python coding patterns and conventions.
vue
Rules for Vue (2 and 3) single-file components.
selectools-development
Selectools development conventions, testing requirements, and release process.
selectools-providers
Rules for working with LLM provider adapters in selectools.
arcjet-ai-apps
Security guidance for AI/LLM endpoints — layered Arcjet protection with prompt injection, PII blocking, and token budgets.