gmail

A Gmail connection for working with email, including messages, drafts, labels, spam, and trash.

In plain words
What is it for?
Use it to find and read emails, send or draft messages, organize mail with labels, and manage existing messages.
Why use it?
It removes the need to switch to Gmail for common email tasks or manually search messages.

Skill for Claude CodeCodex

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/aws-samples/sample-strands-agent-with-agentcore/gmail
Any agent
npx skills add aws-samples/sample-strands-agent-with-agentcore --skill gmail
Clone the repo
git clone --depth 1 https://github.com/aws-samples/sample-strands-agent-with-agentcore

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,481 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 $0.00014 $0.01481
Opus 5 $0.00007 $0.00740
Sonnet 5 $0.00003 $0.00296
Haiku 4.5 $0.00001 $0.00148

Measured 2d ago against content hash f654f83fc629, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

chatbot-app/agentcore/skills/gmail/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gmail

Available Tools

  • list_labels(): List all Gmail labels (system: INBOX, SENT, TRASH, SPAM, DRAFT, IMPORTANT, STARRED, UNREAD; plus user-created labels).

  • list_emails(label?, max_results?, include_spam_trash?): List emails by label.

    • label (string, optional, default: "INBOX"): Label to filter by (INBOX, SENT, DRAFT, TRASH, SPAM, STARRED, IMPORTANT, or custom label ID)
    • max_results (integer, optional, default: 10, max: 100): Number of emails to return
    • include_spam_trash (boolean, optional, default: false): Include SPAM and TRASH
  • search_emails(query, max_results?): Search Gmail using query syntax.

    • query (string, required): Gmail search query (from:, to:, subject:, is:unread, has:attachment, after:, before:, older_than:, newer_than:)
    • max_results (integer, optional, default: 10, max: 50): Number of results
  • read_email(message_id): Read a full email including body and attachments.

    • message_id (string, required): Gmail message ID (from list_emails or search_emails)
  • send_email(to, subject, body, cc?, bcc?, reply_to?, in_reply_to?, html_body?): Send an email.

    • to (string, required): Recipient(s), comma-separated
    • subject (string, required): Email subject
    • body (string, required): Plain text email body
    • cc (string, optional): CC recipient(s)
    • bcc (string, optional): BCC recipient(s)
    • reply_to (string, optional): Reply-To address
    • in_reply_to (string, optional): Message-ID to reply to (for threading)
    • html_body (string, optional): HTML version of email body
  • draft_email(to, subject, body, cc?, bcc?, reply_to?, in_reply_to?, html_body?): Create a draft for later editing/sending. Same parameters as send_email.

  • delete_email(message_id, permanent?): Delete an email.

    • message_id (string, required): Gmail message ID
    • permanent (boolean, optional, default: false): If true, permanently delete; if false, move to Trash
  • bulk_delete_emails(query, reason, max_delete?): Permanently delete multiple emails by query. Cannot be undone.

    • query (string, required): Gmail search query to find emails
    • reason (string, required): Human-readable explanation (shown to user for approval)
    • max_delete (integer, optional, default: 50, max: 100): Maximum emails to delete

Read the full file on GitHub · 112 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. 2d ago First seen · 112 lines · 14 tokens per session scan A f654f83fc629

Subscribe to this mod's changes

gmail is a skill published in the GitHub repository aws-samples/sample-strands-agent-with-agentcore (191 stars, last pushed 6d ago), licensed MIT. It adds 14 tokens to every session and 1,481 once invoked, about $0.0001 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.