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 agentmods add skills/citedy/adclaw/emailnpx skills add citedy/adclaw --skill emailgit clone --depth 1 https://github.com/citedy/adclawWrote 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/citedy/adclaw/email)<a href="https://agentmods.dev/skills/citedy/adclaw/email"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/email.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 | $0.00033 | $0.00741 |
| Opus 5 | $0.00016 | $0.00370 |
| Sonnet 5 | $0.00007 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
email 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Send Email — Skill Instructions
Overview
Send emails directly from your agent — reports, notifications, summaries, alerts. Works with Unosend (5,000 free emails/month) or any SMTP provider.
Use cases:
- "Send the SEO report to [email protected]"
- "Email this summary to the client"
- "Notify [email protected] about the new trends"
- "Send a weekly digest to the team"
When to Use
| Situation | What to do |
|---|---|
| User asks to send/email something | Use send_email tool |
| User wants to notify someone | Compose message + send_email |
| User asks to share a report via email | Generate HTML report + send_email |
Setup
Option A: Unosend (recommended, free tier)
- Sign up at unosend.com
- Add and verify your sending domain
- Get your API key (starts with
un_) - Set environment variables:
UNOSEND_API_KEY=un_your_key[email protected]
5,000 emails/month free, no credit card needed.
Option B: Custom SMTP
Set these environment variables:
SMTP_HOST=smtp.yourprovider.com
SMTP_PORT=587
SMTP_USER=your_username
SMTP_PASSWORD=your_password
[email protected]
Tool Reference
send_email
send_email(
to="[email protected]",
subject="Weekly SEO Report",
body="<h1>Report</h1><p>Your rankings improved 15%...</p>",
html=True
)
Parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
to |
string | yes | Recipient email (comma-separated for multiple) |
subject |
string | yes | Email subject line |
body |
string | yes | Email content (HTML or plain text) |
html |
bool | no | Treat body as HTML (default: true) |
from_email |
string | no | Sender email (default: from env) |
from_name |
string | no | Sender display name (default: AdClaw) |
Response Guidelines
When sending emails:
- Confirm before sending — always tell the user what you're about to send and to whom
- Use HTML for rich content — tables, bold, headers make emails professional
- Keep subject lines clear — "Weekly SEO Report — March 15" not "Report"
- Report success — tell the user the email was sent with recipient and subject
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.
- 4d ago First seen · 106 lines · 33 tokens per session scan A 2266da385db9
email is a skill published in the GitHub repository citedy/adclaw (35 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 741 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 2026-08-30.
Other skills, from other repositories
gmail-tool
Gmail integration tool for unread checks, reading bodies, and drafts via OAuth2 Gmail API access. Use when: reading inbox mail, fetching message bodies, writing drafts, or searching labeled mail.
imap-smtp-email
Read, search, and manage email via IMAP protocol. Send email via SMTP. Supports Gmail, Outlook, 163.com, 126.com, QQ Mail, and any standard IMAP/SMTP server with multi-account support.
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
update-setup
One-time setup wizard for the nanobot upgrade skill. Triggers: setup update, configure update, 设置更新, 初始化更新.
image-generation
Generate images and iteratively edit saved image artifacts.