gmail-draft

gmail-draft is a skill for Claude Code from opendatahub-io/ai-helpers. It costs 53 tokens per session (709 once invoked), scanned A, original, Apache-2.0.

A Gmail drafting tool that creates an email draft from text supplied in the conversation. Gmail is Google's email service.

In plain words
What is it for?
It helps collect or use recipients, a subject, and a body to create a draft in the user's Gmail Drafts folder through gws.
Why use it?
It saves the manual copying and formatting needed to prepare a message in Gmail, while showing the recipients, subject, and body for review first.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the odh-google-workspace plugin — 3 skills shipped together

Good fit It helps collect or use recipients, a subject, and a body to create a draft in the user's Gmail Drafts folder through gws.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opendatahub-io/ai-helpers/gmail-draft
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.

Any agent
npx skills add opendatahub-io/ai-helpers --skill gmail-draft
Clone the repo
git clone --depth 1 https://github.com/opendatahub-io/ai-helpers

Made for: Claude Code.

Or install odh-google-workspace, the plugin that ships this one along with the rest of its 3 skills.

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 gmail-draft

README.md
[![agentmods](https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/gmail-draft/github.svg)](https://agentmods.dev/skills/opendatahub-io/ai-helpers/gmail-draft)
Your own site
<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/gmail-draft"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/gmail-draft/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 gmail-draft

Your own site · 80×15
<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/gmail-draft"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/gmail-draft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 709 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00053 $0.00709
Opus 5 $0.00026 $0.00354
Sonnet 5 $0.00011 $0.00142
Haiku 4.5 $0.00005 $0.00071

Measured 9d ago against content hash 72929dbfe192, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gmail-draft 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/create_draft.py), 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.

plugins/odh-google-workspace/skills/gmail-draft/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gmail Draft

Compose a Gmail draft from text content provided in the conversation.

Prerequisites

  • gws binary must be on $PATH
  • Authenticated with Gmail compose scope: run gws auth login (not --readonly)

If gws is not installed or authentication fails, tell the user to follow the setup instructions in the google-workspace skill.

Helper scripts are located in ${CLAUDE_SKILL_DIR} and require Python 3.10+.


Step 1: Gather Recipients, Subject, and Body

Collect the three required inputs. Sources depend on how the skill was invoked:

  • From another skill (e.g. email-meeting-summary): recipients, subject, and body are passed in context — use them directly.
  • Standalone invocation: use AskUserQuestion to collect any that are missing:
    • Recipients: "Who should receive this email? (comma-separated addresses)"
    • Subject: "What should the subject line be?"
    • Body: "Paste or describe the content you want in the email body."

Step 2: Present for Review

Show the user the draft details before creating:

To: <recipients>
Subject: <subject>

<body>

Ask:

"Does this look right? Reply with any edits, or say 'send' to create the draft."

Incorporate edits and re-present until the user approves.


Step 3: Create the Draft

Write the body to a temp file, then call create_draft.py:

BODY_FILE=$(mktemp /tmp/gmail_draft_body.XXXXXX)
cat > "$BODY_FILE" << 'BODY_EOF'
<approved body text>
BODY_EOF

python3 "${CLAUDE_SKILL_DIR}/scripts/create_draft.py" \
  --to "<recipients>" \
  --subject "<subject>" \
  --body-file "$BODY_FILE"

Step 4: Confirm

On success, tell the user:

"Draft created. You can find it in the Drafts folder in Gmail at https://mail.google.com/mail/#drafts. Review it before sending."

If the script exits with an error, show the error message and suggest the user check gws auth login permissions (the Gmail scope must include draft creation).


Error Reference

Read the full file on GitHub · 104 lines

Files

What ships with it

1 file 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.

  1. 9d ago First seen · 104 lines · 53 tokens per session scan A 72929dbfe192

Subscribe to this mod's changes

gmail-draft is a skill published in the GitHub repository opendatahub-io/ai-helpers (37 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 709 once invoked, about $0.0003 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.