draft-email

draft-email is a command for Claude Code from Elnora-AI/elnora-google-workspace. It costs 33 tokens per session (2,553 once invoked), scanned A, original, Apache-2.0.

A command that creates a Gmail draft in your writing style using context from a CRM and knowledge base. It can draft a new message or a reply, but does not send it.

In plain words
What is it for?
Use it to draft replies to email threads or new emails, with relevant background and verified claims included before you review the draft.
Why use it?
It prepares a context-checked response while leaving the final review and sending decision to you.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the google-workspace plugin — 11 skills, 4 commands, 1 agent shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Elnora-AI/elnora-google-workspace
Claude Code
/plugin install google-workspace

Made for: Claude Code.

Or install google-workspace, the plugin that ships this one along with the rest of its 11 skills, 4 commands, 1 agent.

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 draft-email

README.md
[![agentmods](https://agentmods.dev/badge/commands/elnora-ai/elnora-google-workspace/draft-email.svg)](https://agentmods.dev/commands/elnora-ai/elnora-google-workspace/draft-email)
Your own site
<a href="https://agentmods.dev/commands/elnora-ai/elnora-google-workspace/draft-email"><img src="https://agentmods.dev/badge/commands/elnora-ai/elnora-google-workspace/draft-email.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,553 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00033 $0.02553
Opus 5 $0.00016 $0.01277
Sonnet 5 $0.00007 $0.00511
Haiku 4.5 $0.00003 $0.00255

Measured 5d ago against content hash 0ef0531e2b05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

draft-email scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| URL — internal/company page | Verify it exists by `curl -sI` or `WebFetch`. **Zero tolerance** for unverified links. |
commands/draft-email.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft Email: $ARGUMENTS

Task

Draft a Gmail email — either a reply to an existing thread (<thread-id>) or a new email to someone (<recipient-email> [topic]) — in your voice, with full context loaded and every claim verified.

This skill creates a Gmail DRAFT only. Never sends. The user reviews and approves before any send — never send without explicit approval.

Hard preconditions

You MUST complete every step in order. Skipping is not allowed.

Step 1 — Load your writing-voice guide (optional)

If your knowledge base has a writing-voice guide, load it and apply it. If there's none, skip this step and draft in a clear, professional default voice — the command must still work with no voice doc.

If you have a voice guide, pay particular attention to:

  • Any at-a-glance / quick-reference section — banned phrases, banned punctuation, hard safety rules. This is the 90% of the catch.
  • The relevant by channel subsection (cold outreach / inbound consulting / professional contacts / etc.) for the email type you're drafting.
  • The core voice principles if drafting more than a one-liner.

If your knowledge base is configured (.claude/knowledge-base.local.md), the guide typically lives under {vault_path}/{company_dir}/ — resolve the path from that config.

Step 2 — Identify the recipient(s) and load CRM context

If a thread-id was passed:

python3 ${CLAUDE_PLUGIN_ROOT}/cli/gw.py gmail get-thread <thread-id> --compact

Extract the external participant(s) (sender + non-internal Cc). For each one:

  1. Look them up in vault: {crm_dir}/contacts.csv by email. If found, capture: slug, full name, role, company, stage, last_contact_date, last_contact_channel, last_meeting_date, next_action, priority, notes.
  2. Look up their company in vault: {crm_dir}/companies.csv by name. Capture: slug, stage, NTE/billed/remaining (KPI columns), notes.
  3. If their company stage is active-customer or customer, also read the CRM's company/account detail file (its per-company Markdown file) for the rich relationship context (current state, open contracts, recent invoices, timeline, open items).

Read the full file on GitHub · 218 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. 5d ago First seen · 218 lines · 33 tokens per session scan A 0ef0531e2b05

Subscribe to this mod's changes

draft-email is a command published in the GitHub repository Elnora-AI/elnora-google-workspace (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 33 tokens to every session and 2,553 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.