A workflow for saving, reviewing, sending, scheduling, listing, and deleting email drafts through Mailbridge. It is used when an email should be prepared for later review or delivery.

Use it to compose a draft, save it with a recipient and subject, list existing drafts, send or delete a selected draft, or schedule an email for a specified future time.

It keeps an email from being sent before it is ready and records the draft so you can review, send, schedule, or discard it later. It also handles relative delivery times such as “tomorrow at 9am.”

draft-email — Skill for Claude Code by Creativestefan

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 Creativestefan/mailbridge-mcp --skill draft-email

Clone the repo

git clone --depth 1 https://github.com/Creativestefan/mailbridge-mcp

Made for: Claude Code.

Or install mailbridge, the plugin that ships this one along with the rest of its 8 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/creativestefan/mailbridge-mcp/draft-email.svg)](https://agentmods.dev/skills/creativestefan/mailbridge-mcp/draft-email)

Your own site

<a href="https://agentmods.dev/skills/creativestefan/mailbridge-mcp/draft-email"><img src="https://agentmods.dev/badge/skills/creativestefan/mailbridge-mcp/draft-email.svg" alt="Measured on agentmods" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 548 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.

Model	Per session	Once invoked
Fable 5.1	$0.00090	$0.00548
Opus 5	$0.00045	$0.00274
Sonnet 5	$0.00018	$0.00110
Haiku 4.5	$0.00009	$0.00055

Measured 7d ago against content hash c945451524d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

draft-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 7d 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.

skills/draft-email/SKILL.md · 64 lines

What it actually says

Use the mailbridge MCP tools to save, review, and send drafts — and schedule emails for future delivery.

Draft Workflow

When the user wants to compose but isn't ready to send immediately:

Compose the email content (to, subject, body)
Call save_draft with the email details — returns a draft id

Show the draft summary:

✉️ Draft saved
To: [email protected]
Subject: Your subject
---
Body preview...
---
Say "send draft" to send it, or "delete draft" to discard.

When user says "send it" / "send draft" / confirms → call send_draft with the id
When user says "discard" / "cancel" / "delete" → call delete_draft with the id

Listing Drafts

Call list_drafts — show as numbered list with draft id, recipient, subject, and saved time. When the user picks one to send or delete, use the id.

Scheduled Emails

When the user wants to send at a specific future time:

Collect: to, subject, body, send_at (ISO timestamp)
Resolve relative times: "tomorrow at 9am" → compute the ISO timestamp before calling the tool
Call schedule_email
Confirm: "✅ Scheduled for [time]. It'll send automatically next time your session starts after that time."

Note: Scheduled emails send on the next session start after the scheduled time — not at the exact second. Let the user know if they ask about precision.

To cancel a scheduled email: call list_scheduled to find the id, then cancel_scheduled.

Always Confirm Before Sending

Whether sending immediately or a draft, always show a confirmation step:

To: ...
Subject: ...
---
Body...
---
Send this? (yes / edit)

Only call send_email or send_draft after the user confirms.

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.

7d ago First seen · 64 lines · 90 tokens per session scan A c945451524d7

Subscribe to this mod's changes

draft-email is a skill published in the GitHub repository Creativestefan/mailbridge-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 548 once invoked, about $0.0005 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 2026-08-31.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

mochi-remind

Handle due reminders — notify the user with natural language and mark them done.

kirodotdev/KiroCrew · 20 tokens