mailgun-operational-safety

mailgun-operational-safety is a cursor rule for Cursor from mailgun/mailgun-plugins. It costs 235 tokens per session, scanned A, original, Apache-2.0.

Operational rules for using Mailgun, an email-sending service, through an AI agent. They require caution and confirmation before actions that change account settings, use quota, or send messages.

In plain words
What is it for?
They guide safe Mailgun work such as checking addresses, inspecting previews, reviewing delivery, changing DNS or templates, and sending email.
Why use it?
They reduce the risk of sending unwanted email, changing the wrong setting, exposing sensitive data, or making destructive account changes.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit They guide safe Mailgun work such as checking addresses, inspecting previews, reviewing delivery, changing DNS or templates, and sending email.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mailgun/mailgun-plugins/mailgun-operational-safety
Install

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.

Clone the repo
git clone --depth 1 https://github.com/mailgun/mailgun-plugins

Made for: Cursor.

Wrote 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.

agentmods badge for mailgun-operational-safety

README.md
[![agentmods](https://agentmods.dev/badge/rules/mailgun/mailgun-plugins/mailgun-operational-safety.svg)](https://agentmods.dev/rules/mailgun/mailgun-plugins/mailgun-operational-safety)
Your own site
<a href="https://agentmods.dev/rules/mailgun/mailgun-plugins/mailgun-operational-safety"><img src="https://agentmods.dev/badge/rules/mailgun/mailgun-plugins/mailgun-operational-safety.svg" alt="Measured on agentmods" height="20"></a>
Per session 235 This file is loaded in full into every session.
When invoked 235 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00235 $0.00235
Opus 5 $0.00118 $0.00118
Sonnet 5 $0.00047 $0.00047
Haiku 4.5 $0.00023 $0.00023

Measured 7d ago against content hash bc4e6400eaf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mailgun-operational-safety 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.

plugins/mailgun-claude/rules/mailgun-operational-safety.mdc · 16 lines

What it actually says

Mailgun Operational Safety

Use Mailgun tools cautiously and narrate intent before any action that can change account state, consume quota, or send content externally.

  • Prefer diagnostics before mutating actions.
  • Require explicit user confirmation before sending email, creating preview tests, updating templates, changing DNS/domain/tracking/webhook settings, importing or deleting suppressions, editing routes, changing IP pools, rotating DKIM keys, modifying keys, or changing account/subaccount configuration.
  • Ask for missing operational context before calling tools: domain, region, date range, recipient, sender, template name, tag, provider, event type, or desired product scope.
  • Avoid destructive and admin actions unless the user clearly requested the action and confirmed the target.
  • Use the narrowest relevant tool tag. Prefer validate for address checks, inspect for email preview QA, optimize for inbox placement, and send only when Send API account workflows are needed.
  • Treat recipients, stored messages, logs, template HTML, headers, webhook payloads, and API keys as sensitive.
Changes

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.

  1. 7d ago First seen · 16 lines · 235 tokens per session scan A bc4e6400eaf9

Subscribe to this mod's changes

mailgun-operational-safety is a cursor rule published in the GitHub repository mailgun/mailgun-plugins (1 stars, last pushed 18d ago), licensed Apache-2.0. It adds 235 tokens to every session, about $0.0012 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.