readndraft

readndraft is a plugin for Claude Code from LeoPhoenixT/readNdraft-imap-mcp. Its manifest loads nothing; the 1 skill, 1 MCP server it bundles cost 66 tokens per session together, scanned A, original, Apache-2.0.

An email tool for reading and organizing IMAP mail, and for preparing drafts without sending them.

In plain words
What is it for?
Use it to inspect mail, organize messages, and create unsent email drafts.
Why use it?
It separates preparing email from sending it, reducing the risk of an unintended message being sent.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

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.

Claude Code
/plugin marketplace add LeoPhoenixT/readNdraft-imap-mcp
agentmods
npx agentmods add plugins/leophoenixt/readndraft-imap-mcp/readndraft
Clone the repo
git clone --depth 1 https://github.com/LeoPhoenixT/readNdraft-imap-mcp

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.

agentmods badge for readndraft

README.md
[![agentmods](https://agentmods.dev/badge/plugins/leophoenixt/readndraft-imap-mcp/readndraft.svg)](https://agentmods.dev/plugins/leophoenixt/readndraft-imap-mcp/readndraft)
Your own site
<a href="https://agentmods.dev/plugins/leophoenixt/readndraft-imap-mcp/readndraft"><img src="https://agentmods.dev/badge/plugins/leophoenixt/readndraft-imap-mcp/readndraft.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 1 MCP server cost 66 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

readndraft 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 5d 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.

plugins/readndraft/.claude-plugin/plugin.json · 13 lines

What it actually says

{
  "name": "readndraft",
  "version": "0.9.0",
  "description": "Safely read, organize, and draft IMAP email without sending mail.",
  "author": {
    "name": "LeoPhoenixT",
    "url": "https://github.com/LeoPhoenixT"
  },
  "homepage": "https://github.com/LeoPhoenixT/readNdraft-imap-mcp",
  "repository": "https://github.com/LeoPhoenixT/readNdraft-imap-mcp",
  "license": "Apache-2.0"
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 66 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 5d ago First seen · 13 lines scan A 3f012012f499

Subscribe to this mod's changes

readndraft is a plugin published in the GitHub repository LeoPhoenixT/readNdraft-imap-mcp (0 stars, last pushed 7d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.