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/mhmdreza-rafiei/agent-toolsWrote 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/mhmdreza-rafiei/agent-tools/security)<a href="https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/security"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/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/mhmdreza-rafiei/agent-tools/security"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/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 | $0.00021 | $0.00394 |
| Opus 5 | $0.00010 | $0.00197 |
| Sonnet 5 | $0.00004 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
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 7d 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
Applies when the change touches auth, input parsing, secrets, or a trust boundary. Load for login, payment, file upload, external API calls, migrations of credential stores. Not every chat.
Trust boundaries
- Every input from outside the process (HTTP, CLI args, files, env, queue messages) is untrusted. Validate at the boundary; never carry untrusted data into the core.
- Validate type, length, format, and ranges. Reject early; fail closed.
- Auth checks happen at the edge, not deep in the core. The core assumes the caller is authorized.
Secrets
- Never hardcode secrets. Read from env / secret manager.
- Never log secrets (tokens, passwords, API keys, PII). Redact before logging; assume the log is public.
.envand credential files are never committed. If you see one staged, unstage and warn the user.
Auth
- Hash passwords with a slow KDF (argon2, bcrypt, scrypt). Never MD5/SHA for passwords.
- Tokens: short-lived, scoped, revocable. Rotate via refresh, not long-lived access tokens.
- Constant-time comparison for tokens / hashes. No early-return on mismatch.
Injection
- Parameterize queries. No string-built SQL / shell / LDAP.
- Escape at the output boundary (HTML, URL, JS) — not by hand-rolling.
Do not
- Roll your own crypto. Use the stdlib / audited library.
- Trust client-side validation. The server re-validates everything.
- Ship a secret in a URL / query param (it gets logged).
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.
- 7d ago First seen · 48 lines · 21 tokens per session scan A d28a82edf168
security is a cursor rule published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 23d ago), licensed MIT. It adds 21 tokens to every session and 394 once invoked, about $0.0001 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 2026-09-03.
Other cursor rules, from other repositories
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.
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.