An email drafting tool that prepares a message as a draft in Apple Mail, Outlook, or an .eml file, but never sends it. It uses configured identity, recipient, occasion, language, and visual settings.

Use it to prepare outgoing emails with the appropriate recipient details, footer, attachments, tone, and mail-safe HTML formatting.

It reduces the risk of sending an incorrect email by leaving the final review and sending step to a person. It also avoids rebuilding greetings, signatures, and formatting each time.

mail-draft — Skill for Claude Code by bks-lab/open-bridge

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 bks-lab/open-bridge --skill mail-draft

Clone the repo

git clone --depth 1 https://github.com/bks-lab/open-bridge

Made for: Claude Code.

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/bks-lab/open-bridge/mail-draft/github.svg)](https://agentmods.dev/skills/bks-lab/open-bridge/mail-draft)

Your own site

<a href="https://agentmods.dev/skills/bks-lab/open-bridge/mail-draft"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/mail-draft/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bks-lab/open-bridge/mail-draft"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/mail-draft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,422 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	$0.00082	$0.01422
Opus 5.5	$0.00033	$0.00569
Sonnet 5.5	$0.00016	$0.00284
Haiku 4.5	$0.00008	$0.00142

Measured 8d ago against content hash e2f5f24274f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mail-draft 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 8d ago.

The scan reads SKILL.md. This mod also ships 26 executable files (engine/__init__.py, engine/cli.py, engine/clients/__init__.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/mail-draft/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mail-draft

Builds a mail as a DRAFT in the person's mail client. The person reads it and presses Send. There is no send command, not behind a flag, not in any client module: a draft that is wrong costs a minute, a sent mail that is wrong cannot be taken back. "Send X to Y" is a request for the finished draft.

Engine: skills/mail-draft/mail-draft.sh (Python, stdlib + PyYAML). Model and every field: docs/mail-draft.md.

What decides what

Question	Answered by	Tier
Who signs, how to reach them	`identity/mail-footers/<id>.yaml` (borrows from a persona)	user / org
What occasion, which footer, greeting, attachments	`workflow/mail-profiles/<id>.yaml`	user / org
Who receives it, in which language, formal or not	`identity/mandants/<id>.yaml` (`mail_profile`, `defaults.language`, `defaults.address_form`)	user
Colours and type	`DESIGN.md` through the `design` theme	core / fork
Machine defaults (client, drafts folder)	`bridge-config.yaml` `mail:`	user

CORE ships only the engine, the two _schema.yaml and the two _template.yaml. Every real footer and profile is a USER file (or org when a team shares one through an overlay), and the schema refuses scope: core for a footer.

Decision tree

Request about mail
├── write / draft / "send" a mail ──────────► § Draft a mail
├── "how will X be addressed?" ─────────────► mail-draft.sh explain --to X
├── new footer / signature / profile ───────► § Set up
├── paste a signature into Outlook/Mail ────► mail-draft.sh signature <footer> --out <dir>
└── "is my mail setup ok?" ─────────────────► mail-draft.sh validate && mail-draft.sh list

Draft a mail

Resolve the recipient and occasion first: mail-draft.sh explain --to <who>. It prints the profile, footer, language, form of address and sender, each with the reason. If the profile names a style_skill, load that skill before writing the text.
Write the body as Markdown into a file (greeting and sign-off come from the profile; leave them out unless the text needs its own). Syntax: headings, lists, tables, > [!NOTE] alerts, [[Button]](url), [done] badges, {{snippet:<name>}} from the profile.
Preview and show the person the text part in chat: mail-draft.sh preview --to <who> --subject "<s>" --body-file <f> [--attach <file>]
On their go: mail-draft.sh compose ... with the same arguments. Preflight errors stop it (missing attachment, leftover {placeholder}, required attachment absent). Warnings are printed for the person.
Report what the command printed: client, recipients, attachments, whether the Drafts folder counted it, and for Outlook that "From" must be switched by hand. Never claim a draft that was not verified.

Read the full file on GitHub · 109 lines

Files

What ships with it

37 files 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.

8d ago First seen · 109 lines · 82 tokens per session scan A e2f5f24274f4

Subscribe to this mod's changes

mail-draft is a skill published in the GitHub repository bks-lab/open-bridge (13 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 1,422 once invoked, about $0.0003 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 2026-10-08.

Claude Code Productivity Writing and docs agent-memory agent-orchestration agentic-ai ai-agents codex

mail-draft

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

mail-draft

What decides what

Decision tree

Draft a mail

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

slack

agentmail

kungfu-agent-onboarding

cog-braindump-capture

context-preservation

cog-knowledge-consolidation