email

email is a command for Claude Code from coreyepstein/advanced-gmail-mcp. It costs 8 tokens per session (794 once invoked), scanned A, original, MIT.

A command for managing Gmail messages through connected Gmail tools. It can work across multiple Gmail accounts.

In plain words
What is it for?
Use it to list, search, read, and organise messages; inspect threads and labels; draft or send emails; reply; archive; move messages to trash; and change several messages at once.
Why use it?
It gathers common email work into one command, reducing the need to switch between inboxes and manually repeat actions.

Command for 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 commands/coreyepstein/advanced-gmail-mcp/email
Clone the repo
git clone --depth 1 https://github.com/coreyepstein/advanced-gmail-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 email

README.md
[![agentmods](https://agentmods.dev/badge/commands/coreyepstein/advanced-gmail-mcp/email.svg)](https://agentmods.dev/commands/coreyepstein/advanced-gmail-mcp/email)
Your own site
<a href="https://agentmods.dev/commands/coreyepstein/advanced-gmail-mcp/email"><img src="https://agentmods.dev/badge/commands/coreyepstein/advanced-gmail-mcp/email.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 794 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 $0.00008 $0.00794
Opus 5 $0.00004 $0.00397
Sonnet 5 $0.00002 $0.00159
Haiku 4.5 $0.00001 $0.00079

Measured 4d ago against content hash ad3737ff038f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

.claude/commands/email.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/email - Gmail Management

Manage email across your Gmail accounts using the gmail MCP tools.

User's input: $ARGUMENTS

MCP Tools (gmail)

Before using any tool, run ToolSearch with query +gmail to load them.

Tool Purpose
list_emails List inbox/label (account, label, max_results, query)
search_emails Gmail query search (query, account, max_results)
read_email Read full email by ID (message_id, account)
get_thread Get full thread by ID (thread_id, account)
get_labels List all labels (account)
send_email Send new email (to, subject, body, account)
draft_email Create draft (to, subject, body, account)
reply_email Reply to email (message_id, body, account)
archive_email Archive email (message_id, account)
label_email Add/remove labels (message_id, add_labels, remove_labels, account)
trash_email Trash email (message_id, account)
batch_modify Batch archive/trash/label (message_ids, action, account)

Actions

No args or "triage" → Inbox Triage

  1. Ask which account(s) to triage (or default to all)
  2. For each account, list_emails with max_results=25
  3. Summarize inbox: group by sender/category, flag urgent items
  4. Ask user what to archive/trash/reply to
  5. Execute batch actions

"cleanup" → Daily Email Triage (full workflow)

Phase 1 — Cleanup: Search all accounts for promotions, newsletters, notifications, social, cold outreach. Present grouped summary. Batch archive on approval. Phase 2 — Triage: List remaining inbox per account. Categorize: urgent / action needed / FYI / quick decisions. Present summary tables. Phase 3 — Walkthrough: Read full content of urgent/action items. Brief user with context + recommended action. Group quick decisions separately. Phase 4 — Decisions: Walk through quick decisions one at a time. Wait for user response before next. For each: archive, reply (draft first, get approval), or forward.

Read the full file on GitHub · 67 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. 4d ago First seen · 67 lines · 0 tokens per session scan A ad3737ff038f

Subscribe to this mod's changes

email is a command published in the GitHub repository coreyepstein/advanced-gmail-mcp (7 stars, last pushed 6mo ago), licensed MIT. It adds 8 tokens to every session and 794 once invoked, about $0.0000 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.