Borrowing it
Nothing to install: this file belongs to choyiny/saasmail. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/choyiny/saasmail/main/.claude/skills/use-saasmail/SKILL.mdgit clone --depth 1 https://github.com/choyiny/saasmailWrote 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/choyiny/saasmail/use-saasmail)<a href="https://agentmods.dev/skills/choyiny/saasmail/use-saasmail"><img src="https://agentmods.dev/badge/skills/choyiny/saasmail/use-saasmail.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 58 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00112 | $0.02901 |
| Opus 5 | $0.00056 | $0.01451 |
| Sonnet 5 | $0.00022 | $0.00580 |
| Haiku 4.5 | $0.00011 | $0.00290 |
Grade A, and why
use-saasmail 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 8d 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.
**curl, no attachments:** How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using the saasmail HTTP API
saasmail is a self-hosted email server on Cloudflare Workers. Once a user has a deployed instance, they interact with it from their own apps over HTTP. This skill covers the three things callers do most:
- Send a one-off email (with or without attachments).
- Send an email rendered from a saved template.
- Enroll a person in a sequence (a multi-step drip campaign), and manage that enrollment.
If the user hasn't deployed saasmail yet, point them at /saasmail-onboarding first — without a running instance there's no API to call.
Two pieces of info you always need
Before writing any request, get these from the user (or confirm them):
- Base URL — the host their instance is deployed at, e.g.
https://mail.example.com. There is no shared SaaS endpoint; every instance is the user's own Worker. - API key — a string like
sk_abc123.... Generated in the saasmail UI under Settings → API Keys (orPOST /api/api-keys). It's shown once at creation. Send it asAuthorization: Bearer sk_...on every request.
If the user hasn't created a key yet, tell them where to do it rather than guessing. Keys are gated behind a passkey in non-dev environments, so they may need to register a passkey first.
The other parameter that comes up in nearly every request is fromAddress. It must be one of the sender identities configured in that instance (the addresses the user verified during onboarding, like [email protected]). Sending from an unverified address returns a permission error — don't invent one.
1. Send a one-off email
POST /api/send — content type multipart/form-data (not JSON). The body has:
- A
payloadfield whose value is a JSON-encoded string of the email body. - Zero or more
filesfields, each an attachment.
This shape is unusual but deliberate: it lets the same endpoint handle plain sends and sends with attached files without a separate route.
Minimum payload
{
"to": "[email protected]",
"fromAddress": "[email protected]",
"subject": "Welcome",
"bodyHtml": "<p>Hello!</p>"
}
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.
- 8d ago First seen · 232 lines · 112 tokens per session scan A 80ad461743b0
use-saasmail is a skill published in the GitHub repository choyiny/saasmail (247 stars, last pushed yesterday), licensed Apache-2.0. It adds 112 tokens to every session and 2,901 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
moemail
Use when an AI agent needs a temporary/disposable email address — for receiving verification emails, testing email integrations, or any task requiring a temporary inbox via the moemail CLI.
agent-mailbox
Create and use disposable, token-scoped email addresses through a configured Agent Mailbox MCP server. Use for testing signups, email verification, magic links, password resets, one-time codes, inbound messages, attachments, and transactional email flows.
RespondThat MCP
Connect any AI agent to RespondThat — draft on-brand customer-support email replies, read the merchant's brand knowledge base, list mailboxes, and check balance via the RespondThat API. Triggers when a user wants an agent to answer, draft, or send customer emails, or to integrate AI customer support.
saas-builder
Clone, verify, map, and build on top of ixartz/SaaS-Boilerplate for a user's SaaS idea. Use when a user wants to reuse SaaS Boilerplate, evaluate how their product fits it, or build product-specific pages, database schema, roles, permissions, MVP features, and launch scope on top of the boilerplate.
atomicmail
Read and write email through the Atomic Mail from an AI agent. Handles proof-of-work authentication and JMAP so the agent thinks in JMAP method calls. Use when the user asks to register an email inbox, list mailboxes, fetch or send email.
newsletter
Use when running an email newsletter as a recurring publication — subject + preview pair, issues that turn opens into clicks, the welcome sequence, cadence and engagement tiering, growth loops, and a post-Apple-MPP click scorecard. NOT one-off launch or nurture sends (that is marketing), NOT SPF/DKIM/DMARC (that is…