A tool for managing Gmail, Google's email service, from the command line. It supports reading, searching, sending, labeling, and drafting email, including work with multiple accounts.

Searching and reading messages, sending email, creating drafts, managing labels, and selecting among configured Gmail accounts.

It lets coding agents perform email tasks without manually switching between browser accounts and inboxes.

gmail-skill — Skill for Claude Code and Codex by benchflow-ai: A tool for managing Gmail, Google's email service, from…

About the project

SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.

benchflow-ai/skillsbench · 1,747 stars · on GitHub

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/benchflow-ai/skillsbench/gmail-skill

Any agent

npx skills add benchflow-ai/skillsbench --skill gmail-skill

Clone the repo

git clone --depth 1 https://github.com/benchflow-ai/skillsbench

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/gmail-skill.svg)](https://agentmods.dev/skills/benchflow-ai/skillsbench/gmail-skill)

Your own site

<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/gmail-skill"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/gmail-skill.svg" alt="Measured on agentmods" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,005 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.

Model	Per session	Once invoked
Fable 5	$0.00033	$0.01005
Opus 5	$0.00016	$0.00502
Sonnet 5	$0.00007	$0.00201
Haiku 4.5	$0.00003	$0.00101

Measured 5d ago against content hash 76f6e18cb7ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gmail-skill 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.

The scan reads SKILL.md. This mod also ships 13 executable files (scripts/action-logger.js, scripts/auth/auth-utils.js, scripts/auth/setup-oauth.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

tasks-extra/scheduling-email-assistant/environment/skills/gmail-skill/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gmail Manager Skill

This skill provides comprehensive Gmail integration through lightweight CLI scripts. All operations are token-efficient and composable.

First-Time Setup

Before using this skill, you must set up OAuth authentication:

Install dependencies:

cd ~/.claude/skills/gmail-skill && npm install

Set up Google Cloud credentials:
- Follow the guide in docs/google-cloud-setup.md
- Download credentials.json and save to scripts/auth/credentials.json

Authenticate:

cd ~/.claude/skills/gmail-skill && npm run setup

This will open a browser for Google OAuth and save your token locally.

Multi-Account Support

The Gmail skill supports multiple accounts (e.g., personal and work email):

Add Additional Accounts

# Add a second account (from skill directory)
npm run setup -- --account work

# Add a third account
npm run setup -- --account personal

Each account needs separate OAuth authentication.

Manage Accounts

# List all configured accounts
node scripts/manage-accounts.js --list

# Set default account (used when --account is not specified)
node scripts/manage-accounts.js --set-default work

# Remove an account
node scripts/manage-accounts.js --remove old-account

Using Specific Accounts

All Gmail operations support the --account parameter:

# Send email from work account
node gmail-send.js --account work --to "[email protected]" --subject "..." --body "..."

# Send from personal (or omit --account to use default)
node gmail-send.js --account personal --to "[email protected]" --subject "..." --body "..."

# Search work emails
node gmail-search.js --account work --query "is:unread"

If --account is not specified, the default account is used.

Usage Guidelines

1. Read Documentation On-Demand

When first using Gmail operations, read the comprehensive README:

cat ~/.claude/skills/gmail-skill/README.md

This provides detailed usage examples for all operations.

Read the full file on GitHub · 169 lines

Files

What ships with it

17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

5d ago First seen · 169 lines · 33 tokens per session scan A 76f6e18cb7ee

Subscribe to this mod's changes

gmail-skill is a skill published in the GitHub repository benchflow-ai/skillsbench (1,747 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,005 once invoked, about $0.0002 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 2026-08-30.

Productivity benchmark skillsbench

ceo-setup

One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 60 tokens

gmail-skill