email-with-resend

email-with-resend is a skill for Claude Code, Codex from tushaarmehtaa/tushar-skills. It costs 44 tokens per session (816 once invoked), scanned A, original, MIT.

A guide for building email features with Resend, an email delivery service. It covers transactional, security, lifecycle, and marketing messages, along with templates, consent, preferences, queues, audiences, campaigns, webhooks, and delivery handling.

In plain words
What is it for?
Use it to implement or audit sign-in and security emails, user lifecycle messages, permission-aware marketing email, reusable HTML and text templates, sending queues, webhooks, and delivery records.
Why use it?
It helps applications send email reliably while respecting consent, unsubscribe choices, suppression lists, and sender-domain requirements. It also handles provider errors and prevents duplicate event-triggered messages.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to implement or audit sign-in and security emails, user lifecycle messages, permission-aware marketing email, reusable HTML and text templates, sending queues, webhooks, and delivery records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tushaarmehtaa/tushar-skills/email-with-resend
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.

Any agent
npx skills add tushaarmehtaa/tushar-skills --skill email-with-resend
Clone the repo
git clone --depth 1 https://github.com/tushaarmehtaa/tushar-skills

Made for: Claude Code, Codex.

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 email-with-resend

README.md
[![agentmods](https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/email-with-resend/github.svg)](https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/email-with-resend)
Your own site
<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/email-with-resend"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/email-with-resend/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.

agentmods 80×15 button for email-with-resend

Your own site · 80×15
<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/email-with-resend"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/email-with-resend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 816 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00044 $0.00816
Opus 5.5 $0.00018 $0.00326
Sonnet 5.5 $0.00009 $0.00163
Haiku 4.5 $0.00004 $0.00082

Measured 2d ago against content hash f7494c35789e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

email-with-resend 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 2d 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.

email-with-resend/SKILL.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Email with Resend

Implement email as a reliable, permission-aware subsystem. This is not a cold-outreach workflow.

Workflow

  1. Inspect framework/runtime, installed Resend SDK version, queues/jobs, database and user fields, auth/admin roles, existing templates, email events, consent/preferences, suppression data, webhooks, and verified-domain configuration.
  2. Classify each requested message as transactional, security, lifecycle, or marketing. Do not scaffold re-engagement or campaigns by default. Ask about sender identity, jurisdiction/consent, and preference policy only when not established by the product.
  3. Read the Resend guide for send/batch/webhook patterns, sender authentication and the dated Gmail/Yahoo/Outlook sender rules, Contacts/Segments/Topics, suppression handling, unsubscribe design, and copy guidance relevant to the selected class. Facts there carry a check date; re-check any older than 90 days, or when the installed SDK differs, before relying on it. For raw API shapes, use Resend's official agent skill if installed, otherwise its docs.
  4. Centralize provider calls. Detect the installed SDK API, handle both returned error values and thrown transport/runtime errors, use idempotency keys for event-triggered sends, and return a typed result to the caller.
  5. Escape untrusted template values or use React/provider templates. Generate both HTML and useful text. Keep sender/reply-to configuration server-side and use a verified sending subdomain where appropriate. Treat SPF, DKIM, and an aligned DMARC record (p=none minimum) as required before any marketing or bulk volume, not as optional hardening.
  6. Do not block or silently abandon the primary transaction. Use a durable outbox/queue, or a runtime-supported post-response primitive with observability when loss is acceptable. Unawaited promises are not reliable in serverless runtimes.
  7. For campaigns, use Broadcasts to a Segment, scoped to a Topic for per-category opt-out, or a durable campaign job, rather than a long request loop. Do not hand-build per-category unsubscribe when Topics fit. Enforce consent, preferences, suppression, per-recipient idempotency, rate limits, cancellation, and an audit record. Require role-based admin authorization and confirmation of segment/count before send.
  8. Verify Resend webhook signatures over the raw body, deduplicate events, and process bounces/complaints/delivery failures into a suppression model. Never trust an unsigned event.
  9. Provide one-click unsubscribe (List-Unsubscribe plus List-Unsubscribe-Post: List-Unsubscribe=One-Click, RFC 8058) and a visible body link on marketing and subscribed mail, and stop sending within 48 hours. Do not expose raw email addresses in URLs when an opaque signed identifier can be used. Keep transactional/security opt-outs separate from marketing preferences.

Read the full file on GitHub · 30 lines

Files

What ships with it

1 file beside SKILL.md 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.

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. 2d ago Changed · +2 tokens per session f7494c35789e
  2. 2mo ago First seen · 30 lines · 42 tokens per session scan A fe4f163c5c45

Subscribe to this mod's changes

email-with-resend is a skill published in the GitHub repository tushaarmehtaa/tushar-skills (12 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 816 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Related

email-with-resend compared with skills from other repositories

email-with-resend next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
email-with-resendtushaarmehtaa/tushar-skillsSkill122d agoMITA44Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill69ktodayApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2ktodayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2ktodayMITA46Claude Code
api-designericrisco/rsc-harnessSkill5033d agoMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill253todayMITA106Claude Code
telnyx-messaging-hosted-curlteam-telnyx/aiSkill224todayMITA45Claude Code