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/theognis1002/mcp-gateway/maingit clone --depth 1 https://github.com/theognis1002/mcp-gatewayWrote 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/theognis1002/mcp-gateway/main)<a href="https://agentmods.dev/rules/theognis1002/mcp-gateway/main"><img src="https://agentmods.dev/badge/rules/theognis1002/mcp-gateway/main.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 | $0.00136 | $0.00136 |
| Opus 5 | $0.00068 | $0.00068 |
| Sonnet 5 | $0.00027 | $0.00027 |
| Haiku 4.5 | $0.00014 | $0.00014 |
Grade A, and why
main 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 4d 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
- Refer to
ARCHITECTURE.mdfor project structure. Put business logic in proper files according to this file. Update file with any necessary changes. - Refer to
DATABASE_ERD.mdfor database structure. Update file with any necessary changes. - This is a SINGLE TENANT application since it is for open source purposes.
- Do NOT add too many comments for each function - have 1-2 comments per function at most unless the function is very complicated.
- Use
bunfor frontend app - Types should go into
apps/backend/internal/typesdirectory
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.
- 4d ago First seen · 12 lines · 136 tokens per session scan A 89bd5828c954
main is a cursor rule published in the GitHub repository theognis1002/mcp-gateway (41 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 136 tokens to every session, about $0.0007 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 2026-08-30.
Other cursor rules, from other repositories
05-web-development
Use the following format for code blocks.
03-project-structure
The repository is organized in a monorepo using pnpm workspaces: pnpm-workspace.yaml. It contains the following.
vios-sqa
VIOS SQA agent. One-click build → deploy → test → UI validation cycle. Use when asked to run regression tests, check test results, deploy for testing, or verify UI behavior.
github-workflow
MCP tool management and workflow proxy.
nodejs
This guide will walk you through installing Node.js using NVM (Node Version Manager) and setting up pnpm as your package manager.
cursorrules
Follow AIINTEGRATION.md.