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/kristiyan-velkov/ai-security-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/kristiyan-velkov/ai-security-rules/mcp-and-tool-security)<a href="https://agentmods.dev/rules/kristiyan-velkov/ai-security-rules/mcp-and-tool-security"><img src="https://agentmods.dev/badge/rules/kristiyan-velkov/ai-security-rules/mcp-and-tool-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/kristiyan-velkov/ai-security-rules/mcp-and-tool-security"><img src="https://agentmods.dev/badge/rules/kristiyan-velkov/ai-security-rules/mcp-and-tool-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 | $0.00000 | $0.00367 |
| Opus 5.5 | $0.00000 | $0.00147 |
| Sonnet 5.5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
mcp-and-tool-security scanned grade A with 1 finding 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 10d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
globs: "**/.cursor/mcp.json,**/mcp.json,**/.mcp/**,**/claude_desktop_config.json,**/.claude/settings.json,**/.claude/settings.local.json" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 10d ago First seen · 27 lines · 0 tokens per session scan A b14b7c7c0895
mcp-and-tool-security is a cursor rule published in the GitHub repository kristiyan-velkov/ai-security-rules (4 stars, last pushed 11d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 367 tokens. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-17.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.
no-family-vocabulary-in-framework
The framework domain (packages/1-framework) carries no family- or target-specific vocabulary — types, fields, hooks, or strategy values — and, outside the CLI and the PSL parser's grammar names, no Prisma version name before 8. Enforced by the no-family-vocabulary Biome plugin plus the lint:ratchets ratchet.