email-compose-review

email-compose-review is a skill for Claude Code, Codex from jayvee6/apple-mail-mcp. It costs 121 tokens per session (1,479 once invoked), scanned A, original, MIT.

A review process for emails drafted with an AI assistant before they are opened in Apple Mail.

In plain words
What is it for?
Use it to draft or revise email messages and replies, show the revised version for approval, and leave sending to the user.
Why use it?
It catches unclear wording, factual problems, filler, and signs of machine-written text before the draft reaches the user or is sent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

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.

agentmods
npx agentmods add skills/jayvee6/apple-mail-mcp/skill
Any agent
npx skills add jayvee6/apple-mail-mcp --skill skill
Clone the repo
git clone --depth 1 https://github.com/jayvee6/apple-mail-mcp

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-compose-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/jayvee6/apple-mail-mcp/skill.svg)](https://agentmods.dev/skills/jayvee6/apple-mail-mcp/skill)
Your own site
<a href="https://agentmods.dev/skills/jayvee6/apple-mail-mcp/skill"><img src="https://agentmods.dev/badge/skills/jayvee6/apple-mail-mcp/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,479 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00121 $0.01479
Opus 5 $0.00060 $0.00740
Sonnet 5 $0.00024 $0.00296
Haiku 4.5 $0.00012 $0.00148

Measured 6d ago against content hash 1422df875400, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

email-compose-review 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 6d 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.

skill/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Email Compose Review

You are drafting an email on behalf of a human. Before it reaches Mail, your draft must survive a multi-pass review. The goal: remove AI writing tells, tighten the prose, verify facts, and ensure the message lands clearly — all without adding filler or bloat.

This skill runs on LLM-drafted text only. If the user wrote the body themselves and asks for a review, apply it. If they hand you a body to send as-is, skip the review and open the draft directly.


The Non-Negotiables

  1. Never call compose_email or reply_email with your first draft. Write, review, revise — then open the draft.
  2. Always pass send: false. The user sends from Mail after reading it. Automatic sending of LLM-drafted email is not acceptable.
  3. Always show the revised draft and wait for explicit approval before calling any MCP tool.

Step 1 — Write the first draft

Write the email body internally. Don't call any MCP tools yet. Just write it.


Step 2 — Run the review swarm

In Claude Code (sub-agents available): spawn all five reviewers as parallel sub-agents in a single message. Each receives the draft and returns specific flagged issues plus suggested fixes. Collect all five outputs, then proceed to Step 3.

In Claude Desktop (no sub-agents): run the five reviews as sequential internal passes. Be honest and rigorous — don't just nod through each one.


Reviewer 1 — Slop Detector

AI-written email has recognizable tells. Find and remove them all.

Opening clichés to cut:

  • "I hope this email finds you well"
  • "I hope you're doing well / having a great day"
  • "I wanted to reach out"
  • "Thanks for reaching out"

Sycophantic filler:

  • "Certainly!", "Absolutely!", "Of course!", "Great question!"
  • Any opener that exists only to sound agreeable before the actual content

Hedge padding:

  • "It's worth noting that", "It's important to mention", "I just wanted to"
  • "Please don't hesitate to", "Feel free to"
  • "I was wondering if perhaps you might be able to..."

Read the full file on GitHub · 188 lines

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. 6d ago First seen · 188 lines · 121 tokens per session scan A 1422df875400

Subscribe to this mod's changes

email-compose-review is a skill published in the GitHub repository jayvee6/apple-mail-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 1,479 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

integration-testing

Use when setting up, running, or debugging integration tests against real Apple Mail. Also use when unit tests pass but behavior seems wrong, when adding new AppleScript operations, or when you need to understand why mocked tests are insufficient for this project.

s-morgan-jeffries/apple-mail-fast-mcp · 52 tokens

performance-patterns

Use when optimizing Apple Mail MCP operations, diagnosing slow queries, adding new filtering logic, or modifying how data is fetched from Mail.app. Covers osascript overhead, whose clause optimization, batch operation patterns, and known operation timings.

s-morgan-jeffries/apple-mail-fast-mcp · 50 tokens

api-design

Use BEFORE adding any new tool, parameter, or endpoint to the Apple Mail MCP server. Also use when considering API changes, evaluating feature requests, or when tempted to create a specialized operation. Contains the decision tree that prevents tool sprawl and the anti-pattern catalog.

s-morgan-jeffries/apple-mail-fast-mcp · 56 tokens

release

Use when the user wants to release a new version. Orchestrates the full release workflow including milestone check, version bump, changelog generation, validation, tagging, and PR creation. Also use when discussing release planning or version management.

s-morgan-jeffries/apple-mail-fast-mcp · 49 tokens

email-management-expert

Expert email management assistant for Apple Mail. Use this when the user mentions inbox management, email organization, email triage, inbox zero, organizing emails, managing mail folders, email productivity, checking emails, or email workflow optimization. Provides intelligent workflows and best practices for…

patrickfreyer/apple-mail-mcp · 61 tokens

apple-mail

Use this skill when the user wants to manage Apple Mail on macOS - reading, searching, sending, replying to, forwarding, and organizing emails and mailboxes. This skill provides access to Apple Mail through MCP tools.

sweetrb/apple-mail-mcp · 47 tokens