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/mailgun/mailgun-pluginsWrote 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/plugins/mailgun/mailgun-plugins/mailgun-gemini)<a href="https://agentmods.dev/plugins/mailgun/mailgun-plugins/mailgun-gemini"><img src="https://agentmods.dev/badge/plugins/mailgun/mailgun-plugins/mailgun-gemini/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/plugins/mailgun/mailgun-plugins/mailgun-gemini"><img src="https://agentmods.dev/badge/plugins/mailgun/mailgun-plugins/mailgun-gemini.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mailgun-gemini 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 1mo 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
{
"name": "mailgun-gemini",
"version": "0.1.1",
"description": "Gemini CLI extension for Mailgun email, deliverability, suppression, template, Inspect, Optimize, Validate, and reporting workflows.",
"author": {
"name": "Mailgun",
"email": "[email protected]",
"url": "https://github.com/mailgun"
},
"license": "Apache-2.0",
"homepage": "https://www.mailgun.com/",
"repository": "https://github.com/mailgun/mailgun-plugins",
"mcpServers": {
"mailgun": {
"command": "npx",
"args": ["-y", "@mailgun/[email protected]"],
"env": {
"MAILGUN_API_KEY": "${MAILGUN_API_KEY}"
},
"timeout": 15000
}
},
"settings": [
{
"name": "MAILGUN_API_KEY",
"description": "Mailgun private API key.",
"envVar": "MAILGUN_API_KEY",
"sensitive": true
}
]
}
What ships with it
23 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- commands/mailgun/audit-domain-health.toml 469 B
- commands/mailgun/compare-delivery-across-domains.toml 414 B
- commands/mailgun/draft-test-email-template.toml 369 B
- commands/mailgun/investigate-bounces-last-7-days.toml 471 B
- commands/mailgun/review-suppressions-for-domain.toml 390 B
- commands/mailgun/setup.toml 492 B
- commands/mailgun/verify-dns-for-domain.toml 345 B
- README.md 716 B
- skills/address-validation/SKILL.md 2.7 KB
- skills/bounce-rate-explanation/SKILL.md 2.1 KB
- skills/bounce-suppression-analysis/SKILL.md 1.8 KB
- skills/campaign-preflight/SKILL.md 2.6 KB
- skills/cross-domain-reporting/SKILL.md 1.8 KB
- skills/deliverability-triage/SKILL.md 2.4 KB
- skills/domain-onboarding-dns-verification/SKILL.md 2.3 KB
- skills/engagement-analysis/SKILL.md 1.8 KB
- skills/inbound-routing-troubleshooting/SKILL.md 2.4 KB
- skills/mcp-troubleshooting/SKILL.md 1.8 KB
- skills/missing-email-investigation/SKILL.md 2.3 KB
- skills/platform-operator/SKILL.md 2.5 KB
- skills/post-send-analysis/SKILL.md 2.4 KB
- skills/sending-health-check/SKILL.md 2.1 KB
- skills/sending-template-qa/SKILL.md 2.8 KB
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.
- 1mo ago First seen · 32 lines scan A 7e6859f01e71
mailgun-gemini is a plugin published in the GitHub repository mailgun/mailgun-plugins (2 stars, last pushed 15d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-16.
Other plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.