gw-gmail

gw-gmail is a skill for Claude Code from Elnora-AI/elnora-google-workspace. It costs 71 tokens per session (2,309 once invoked), scanned A, original, Apache-2.0.

A command-line tool for working with Gmail accounts, including sending, drafting, reading, replying to, and managing email.

In plain words
What is it for?
Use it to send or draft messages, read inboxes and threads, reply to email, scan for replies, attach files, and manage messages such as trashing email.
Why use it?
It lets a coding agent handle email through commands instead of requiring manual work in the Gmail website. It can also route actions through different configured accounts.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

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 — 13 skills, 4 commands, 1 agent shipped together

Good fit Use it to send or draft messages, read inboxes and threads, reply to email, scan for replies, attach files, and manage messages such as trashing email.

Compare 6 skills from other repositories ↓
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 13 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 gw-gmail

README.md
[![agentmods](https://agentmods.dev/badge/skills/elnora-ai/elnora-google-workspace/gw-gmail/github.svg)](https://agentmods.dev/skills/elnora-ai/elnora-google-workspace/gw-gmail)
Your own site
<a href="https://agentmods.dev/skills/elnora-ai/elnora-google-workspace/gw-gmail"><img src="https://agentmods.dev/badge/skills/elnora-ai/elnora-google-workspace/gw-gmail/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.

agentmods 80×15 button for gw-gmail

Your own site · 80×15
<a href="https://agentmods.dev/skills/elnora-ai/elnora-google-workspace/gw-gmail"><img src="https://agentmods.dev/badge/skills/elnora-ai/elnora-google-workspace/gw-gmail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,309 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.02309
Opus 5 $0.00036 $0.01154
Sonnet 5 $0.00014 $0.00462
Haiku 4.5 $0.00007 $0.00231

Measured 10d ago against content hash a31fcc069b06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gw-gmail 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 10d 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.

skills/gw-gmail/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gmail

Invocation

CLI="python3 ${CLAUDE_PLUGIN_ROOT}/cli/gw.py"

Account Routing

Accounts are user-defined in accounts.json (see gw auth list / gw auth login --account <name>); the names and emails below are only examples.

Account Example email Typical use
--account main [email protected] Primary (default)
--account work [email protected] Work / outreach
--account personal [email protected] Personal

Commands

Send & Draft

Always use --body-file - with heredoc. Never --body "..." — special characters break shell quoting.

$CLI gmail send --to EMAIL --subject "..." --body-file - [--cc "[email protected],[email protected]"] [--thread-id TID] [--attach FILE] [--account work] <<'BODY'
Email body here.
BODY

$CLI gmail draft --to EMAIL --subject "..." --body-file - [--cc "[email protected],[email protected]"] [--thread-id TID] [--attach FILE] [--account work] <<'BODY'
Draft body here.
BODY

Multiple recipients: --to and --cc accept comma-separated addresses or repeated flags. Always comma-separate in one string for clarity: --cc "[email protected],[email protected],[email protected]".

Response: {"sent":true,"id":"MSG_ID","threadId":"TID"} or {"drafted":true,"id":"DRAFT_ID","messageId":"MSG_ID"}

Attachments

The CLI fully supports file attachments. Use --attach with an absolute file path. Repeat for multiple files.

# Single attachment
$CLI gmail send --to EMAIL --subject "..." --attach /path/to/file.pdf --body-file - <<'BODY'
See attached.
BODY

# Multiple attachments
$CLI gmail draft --to EMAIL --subject "..." --attach /path/to/report.pdf --attach /path/to/data.csv --body-file - <<'BODY'
Two files attached.
BODY

# Attachment on a draft reply
$CLI gmail draft-reply MESSAGE_ID --attach /path/to/file.pdf --body-file - <<'BODY'
Attaching the document you requested.
BODY

Works on: send, draft, draft-reply. Any file type. Uses MIME multipart/mixed encoding. Supports ~/ paths.

Quote paths with spaces (e.g. Google Drive): --attach "/path/with spaces/file.pdf"

Read the full file on GitHub · 213 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. 10d ago First seen · 213 lines · 71 tokens per session scan A a31fcc069b06

Subscribe to this mod's changes

gw-gmail is a skill published in the GitHub repository Elnora-AI/elnora-google-workspace (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 71 tokens to every session and 2,309 once invoked, about $0.0004 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

managing-google-workspace

Manages Google Workspace operations across 12 services (Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Apps Script, Custom Search). Supports MCP tools or CLI via uvx workspace-mcp --cli. Provides tool routing, workflows, and parameter guidance for 114 tools. Triggers for "check my email"…

taylorwilsdon/google_workspace_mcp · 123 tokens

alive:system-cleanup

The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.

alivecontext/alive · 52 tokens

alive:world

The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.

alivecontext/alive · 63 tokens

alive:bundle

Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.

alivecontext/alive · 34 tokens

alive:settings

The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…

alivecontext/alive · 84 tokens

alive-cleanup

System maintenance -- stale tasks, orphan folders, unsaved sessions, world health check.

alivecontext/alive · 20 tokens