agentmods.dev

email-drafts

email-drafts is a skill for Claude Code, Codex from thomasbek3/hermes-bot-kit. It costs 30 tokens per session (550 once invoked), scanned A, original, MIT.

An email-writing workflow that creates an editable draft for the user rather than sending a message. The user reviews the draft and sends, changes, or discards it.

In plain words
What is it for?
It is for drafting new emails, replies, and forwarded messages, including recipients, attachments, and thread details when available.
Why use it?
It prevents an email from being sent without the user's approval and keeps edits and sending in the email interface.

Skill for Claude CodeCodex

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

not rated 222repo +20 today A scan 30 tokens original MIT

Good fit It is for drafting new emails, replies, and forwarded messages, including recipients, attachments, and thread details when available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thomasbek3/hermes-bot-kit/email-drafts
View source ↗ thomasbek3/hermes-bot-kit
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 thomasbek3/hermes-bot-kit --skill email-drafts
Clone the repo
git clone --depth 1 https://github.com/thomasbek3/hermes-bot-kit

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-drafts

README.md
[![agentmods](https://agentmods.dev/badge/skills/thomasbek3/hermes-bot-kit/email-drafts/github.svg)](https://agentmods.dev/skills/thomasbek3/hermes-bot-kit/email-drafts)
Your own site
<a href="https://agentmods.dev/skills/thomasbek3/hermes-bot-kit/email-drafts"><img src="https://agentmods.dev/badge/skills/thomasbek3/hermes-bot-kit/email-drafts/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-drafts

Your own site · 80×15
<a href="https://agentmods.dev/skills/thomasbek3/hermes-bot-kit/email-drafts"><img src="https://agentmods.dev/badge/skills/thomasbek3/hermes-bot-kit/email-drafts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 550 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00030 $0.00550
Opus 5.5 $0.00012 $0.00220
Sonnet 5.5 $0.00006 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured yesterday against content hash 4e4f01ebcc1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

email-drafts 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 yesterday.

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.

- Never email anyone with a script, `curl`, SMTP, a mail API, a browser, a Composio tool (such as
email-drafts/skills/email-drafts/SKILL.md · 45 lines

What it actually says

Email drafts

Email goes through Composio. Use email_draft_create; never send email any other way.

You never send email yourself. When the user wants an email written, sent, answered or forwarded:

  1. Call email_draft_create with to, subject and body (plain text, no signature: the user's signature is added under it). Add cc, bcc, attachments (files in your working directory for this chat) and in_reply_to (the original's Message-ID, subject, sender and Gmail thread id) when you have them.
  2. Reply with one short line, for example: Draft to Sam is ready on the card above. Do not paste the email again: the user reads and edits it on the card.
  3. The user clicks Send on the card, edits it, or clicks Discard. When they ask for changes, call email_draft_update with the draft id instead of creating a second draft.
  4. To find out what happened, call email_draft_status. Report a failure's error in one line.

Rules:

  • Never email anyone with a script, curl, SMTP, a mail API, a browser, a Composio tool (such as GMAIL_SEND_EMAIL through the composio CLI) or any other tool. The draft card is the only way out, even when the user says "just send it": write the draft and tell them it is ready. The card sends it through Composio for you.
  • When a send failed with "Delivery unknown", do not draft it again: tell the user to check their Sent folder.
  • When the tool answers disabled, drafting is turned off for you: relay its message in one line and do not try another way.
  • When the tool reports the draft was sent automatically (the user allowed every recipient), say so in one line.
  • A scheduled (cron) run only creates drafts: they wait for the user, so finish your run and mention the draft in your report.
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. yesterday First seen · 45 lines · 30 tokens per session scan A 4e4f01ebcc1f

Subscribe to this mod's changes

email-drafts is a skill published in the GitHub repository thomasbek3/hermes-bot-kit (222 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 550 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-11.

ProductivityWriting and docsagentscomputer-usehermeshermes-pluginnovncremote-desktop
Related

email-drafts compared with skills from other repositories

email-drafts next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
email-draftsthomasbek3/hermes-bot-kitSkill222todayMITA30Claude Code, Codex
opendeskvitalops/opendeskSkill9223d agoMITA77Claude Code
email-inbox-triagecyborg-garden/hermes-agent-mtSkill14todayMITA19Claude Code, Codex
siyuancyborg-garden/hermes-agent-mtSkill14todayMITA17Claude Code, Codex
agentmailcyborg-garden/hermes-agent-mtSkill14todayMITA15Claude Code, Codex
google-workspacecyborg-garden/hermes-agent-mtSkill14todayMITA21Claude Code, Codex
teams-meeting-pipelinecyborg-garden/hermes-agent-mtSkill14todayMITA16Claude Code, Codex