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 skills add mailgun/mailgun-plugins --skill sending-template-qagit 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/skills/mailgun/mailgun-plugins/sending-template-qa)<a href="https://agentmods.dev/skills/mailgun/mailgun-plugins/sending-template-qa"><img src="https://agentmods.dev/badge/skills/mailgun/mailgun-plugins/sending-template-qa.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 5.1 | $0.00022 | $0.00577 |
| Opus 5 | $0.00011 | $0.00289 |
| Sonnet 5 | $0.00004 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
sending-template-qa 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- When generating direct API examples, use `multipart/form-data` for the Messages API. In curl examples, use `-F` fields rather than a JSON body. How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sending and Template QA
Use this skill when a user wants to draft an email, review a template, run preview checks, or send a test.
Intake
Ask for the sender domain, from address, recipient or test seed list, subject, template name/version, region, and whether the user wants test mode. For template updates, ask whether to create a new version or modify metadata.
Workflow
- Review the content with the user first.
- Prefer Inspect preview QA for HTML rendering, links, images, accessibility, and code analysis before any send.
- Use Validate for recipient checks when deliverability or syntax is in question.
- If sending, confirm sender, recipient, subject, body/template, test mode, and tags.
- After a send, retrieve delivery events or logs only when the user asks or when validation requires confirmation.
Template Variable QA
- Identify required variables from the template and compare them to the planned send payload.
- Check for inconsistent naming, missing variables, reserved variable names, and unresolved placeholders.
- For batch sends, verify every recipient has the variables used by the subject, text body, HTML body, and template.
- Confirm text and HTML versions carry the same essential information.
- For existing templates, verify the intended template version before creating a new version or sending with it.
Mailgun Gotchas
- Confirm the Mailgun region before sending. US and EU domains must use the matching API region.
- Sandbox domains can send only to authorized recipients.
- When generating direct API examples, use
multipart/form-datafor the Messages API. In curl examples, use-Ffields rather than a JSON body. - For batch personalization, validate
recipient-variablesJSON before sending so recipients do not receive unresolved placeholders. - Avoid template variable names reserved by Mailgun verification flows, including
CODEandOTP. - Verify template names before sending. A missing template may be accepted at queue time and fail later in delivery logs.
- For scheduled sends, use a date format with a numeric timezone offset rather than an abbreviated timezone name.
- Keep send options, headers, variables, and template variables small enough for Mailgun request limits.
- If writing integration code, load API keys from environment variables and use username
apiwith the private key for Basic Auth.
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.
- 7d ago First seen · 50 lines · 22 tokens per session scan A 6baf74ae6089
sending-template-qa is a skill published in the GitHub repository mailgun/mailgun-plugins (1 stars, last pushed 18d ago), licensed Apache-2.0. It adds 22 tokens to every session and 577 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.