platform-operator

platform-operator is a skill for Claude Code, Codex from mailgun/mailgun-plugins. It costs 36 tokens per session (523 once invoked), scanned A, original, Apache-2.0.

A guide for SaaS and platform teams that let their customers send email through Mailgun, an email delivery service.

In plain words
What is it for?
It supports planning tenant account structures, domain onboarding, IP pools, trust limits, monitoring, and account diagnostics.
Why use it?
It helps manage separate customer accounts, sending limits, sender checks, email reputation, and abuse risks across many tenants.

Skill for Claude CodeCodex

Part of the mailgun-claude plugin — 15 skills, 7 commands, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/mailgun/mailgun-plugins/platform-operator
Any agent
npx skills add mailgun/mailgun-plugins --skill platform-operator
Clone the repo
git clone --depth 1 https://github.com/mailgun/mailgun-plugins

Made for: Claude Code, Codex.

Or install mailgun-claude, the plugin that ships this one along with the rest of its 15 skills, 7 commands, 1 MCP server.

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 platform-operator

README.md
[![agentmods](https://agentmods.dev/badge/skills/mailgun/mailgun-plugins/platform-operator.svg)](https://agentmods.dev/skills/mailgun/mailgun-plugins/platform-operator)
Your own site
<a href="https://agentmods.dev/skills/mailgun/mailgun-plugins/platform-operator"><img src="https://agentmods.dev/badge/skills/mailgun/mailgun-plugins/platform-operator.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 523 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.00523
Opus 5 $0.00018 $0.00262
Sonnet 5 $0.00007 $0.00105
Haiku 4.5 $0.00004 $0.00052

Measured 3d ago against content hash 77526c2a765b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

platform-operator 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 3d 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/skills/platform-operator/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Platform Operator

Use this skill when the user runs a SaaS, martech, developer platform, or other service that lets its own customers send email through Mailgun.

Do not use this skill for a single sender managing only its own email program. Use deliverability triage, domain onboarding, or sending QA instead.

Intake

Ask for the tenant model, subaccount structure, domain ownership model, send volume, IP pool setup, abuse handling process, and whether the user wants architecture guidance or account diagnostics.

Workflow

  1. Identify whether each tenant has its own subaccount, domain, API key scope, and suppression boundary.
  2. Review sender onboarding gates: business identity, domain verification, domain age, impersonation risk, and first send limits.
  3. Check progressive trust controls: daily caps for new senders, advancement criteria, and rollback paths for risky senders.
  4. Review monitoring signals across tenants: hard bounces, complaints, spam trap indicators, blocklist signals, provider throttling, volume spikes, and suppression growth.
  5. Inspect IP and pool strategy when available: shared pools, dedicated pools, quarantine pools, warmup status, and tenant isolation.
  6. Summarize operational gaps and recommend next steps, separating advisory changes from actions that modify the Mailgun account.

Operating Guidance

  • A platform is accountable for the mail sent through its Mailgun account, even when tenants provide the content and recipient lists.
  • Require domain verification before meaningful production sending.
  • Treat complaint rates near or above 0.1 percent as urgent, especially for new tenants.
  • Pause or limit tenants with sharp bounce spikes, complaint spikes, spam trap indicators, or sudden volume changes until reviewed.
  • Maintain a monitored abuse mailbox, complaint intake process, human review queue, and tenant notification path.
  • Avoid mixing all tenants into one undifferentiated reputation pool when volume and risk justify stronger isolation.

Read the full file on GitHub · 42 lines

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. 3d ago First seen · 42 lines · 36 tokens per session scan A 77526c2a765b

Subscribe to this mod's changes

platform-operator is a skill published in the GitHub repository mailgun/mailgun-plugins (1 stars, last pushed 14d ago), licensed Apache-2.0. It adds 36 tokens to every session and 523 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens