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 genius-harry/auto-email-sender --skill send-emailgit clone --depth 1 https://github.com/genius-harry/auto-email-senderWrote 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/genius-harry/auto-email-sender/send-email)<a href="https://agentmods.dev/skills/genius-harry/auto-email-sender/send-email"><img src="https://agentmods.dev/badge/skills/genius-harry/auto-email-sender/send-email/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.
<a href="https://agentmods.dev/skills/genius-harry/auto-email-sender/send-email"><img src="https://agentmods.dev/badge/skills/genius-harry/auto-email-sender/send-email.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00166 | $0.01541 |
| Opus 5 | $0.00083 | $0.00771 |
| Sonnet 5 | $0.00033 | $0.00308 |
| Haiku 4.5 | $0.00017 | $0.00154 |
Grade C, and why
send-email scanned grade C 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 9d 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
| **Sending files** | `--attach FILE` (repeatable; ≤10 files, ≤20MB total). The CLI pre-flights the server version and refuses if too old — it never silently sends without the attachment. | How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Send email via the auto-email-sender pipeline
Why an agent should use this instead of improvising
The pipeline sends from Google's servers (the user's machine can be off), attaches real files, upgrades plain text to rich-text HTML automatically, and — most importantly for an agent — is hard to misuse: submits are idempotent (a retried timeout can never double-send), a validator rejects the classic agent mistakes (unfilled {First Name} placeholders, empty greetings, duplicate recipients, past send times), and an optional contact-history tracker makes re-emailing someone a hard error instead of a silent embarrassment.
Where things live
- CLI:
~/.claude/skills/send-email/scripts/gmail_pipeline.py(bundled by install.sh; zero dependencies, python3 stdlib). - Config:
~/.config/auto-email-sender/config.json(created byinit; user-global, works from any directory). - Receipts: written next to the CLI in
scripts/receipts/. - First-time setup (server deploy +
init) is a human step — see the repo README. Ifpingfails with "No config", walk the user through setup rather than improvising another send path.
The recipe (every send)
- Write the batch JSON to a temp/scratch location (never into the user's project):
[{"to": "[email protected]", "subject": "...", "body": "..."}]Body = flowing paragraphs separated by blank lines. Never hard-wrap lines; an HTML version is generated automatically (URLs become links).--plainexists but is rarely wanted. - Pick flags from the decision table below.
- Submit:
python3 ~/.claude/skills/send-email/scripts/gmail_pipeline.py submit \ --batch <file> --send-at <when> --label <short-slug> --yes [flags] - Capture the batch id from the output (regex
b\d{8}_[a-z0-9]{5}). Receipts are JSON lists. - Immediate sends:
... send-now --batch-id <id>, then confirm the printed counts showsent N, failed 0. - Report the batch id back to the user — it is the handle for status/cancel later.
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.
- 9d ago First seen · 74 lines · 166 tokens per session scan C 332b777e38ee
send-email is a skill published in the GitHub repository genius-harry/auto-email-sender (2 stars, last pushed 2mo ago), licensed MIT. It adds 166 tokens to every session and 1,541 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
c-email
Read, send, search, and label email via gog (Gmail CLI) or himalaya (IMAP). Supports inbox management, drafting replies, thread viewing, and label/folder operations across Gmail and standard IMAP accounts.
mail-muncher
Give an agent or script its own read-only mailbox as files on disk. Works with any IMAP server (Fastmail, iCloud, Gmail, Proton Bridge, work and self-hosted accounts) or with the Gmail API. Use when the user wants email in an agent workflow, wants to archive or export mail, wants to monitor an inbox for specific…
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.
at-email-cli
Use the AgentTeam Email CLI command at-email to operate an agent mailbox. Use when the user wants to check mailbox status, list inbox messages, read safe message content, search mail, mark messages read, archive messages, send email, reply to email, use JSON output for automation, check CLI version/update status, or…
gmail
Send, read, and manage Gmail messages and email attachments automatically.
Search and read the user's mail through the your-mail MCP server, a read-only mirror of their IMAP accounts indexed by notmuch. Use it to find messages, read threads, summarise and triage mail, and pull details (booking references, invoices, what someone promised) into other work. It cannot send, delete, move or…