Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cblecker/claude-pluginsnpx agentmods add skills/cblecker/claude-plugins/gws-gmail-sendWrote 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.
[](https://agentmods.dev/skills/cblecker/claude-plugins/gws-gmail-send)<a href="https://agentmods.dev/skills/cblecker/claude-plugins/gws-gmail-send"><img src="https://agentmods.dev/badge/skills/cblecker/claude-plugins/gws-gmail-send/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.
<a href="https://agentmods.dev/skills/cblecker/claude-plugins/gws-gmail-send"><img src="https://agentmods.dev/badge/skills/cblecker/claude-plugins/gws-gmail-send.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00013 | $0.00751 |
| Opus 5.5 | $0.00005 | $0.00300 |
| Sonnet 5.5 | $0.00003 | $0.00150 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
gws-gmail-send 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 1mo 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.
This is a copy
100% identical to gws-gmail-send — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gmail +send
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto create it.
Send an email
Usage
gws gmail +send --to <EMAILS> --subject <SUBJECT> --body <TEXT>
Flags
| Flag | Required | Default | Description |
|---|---|---|---|
--to |
✓ | — | Recipient email address(es), comma-separated |
--subject |
✓ | — | Email subject |
--body |
✓ | — | Email body (plain text, or HTML with --html) |
--from |
— | — | Sender address (for send-as/alias; omit to use account default) |
--attach |
— | — | Attach a file (can be specified multiple times) |
--cc |
— | — | CC email address(es), comma-separated |
--bcc |
— | — | BCC email address(es), comma-separated |
--html |
— | — | Treat --body as HTML content (default is plain text) |
--dry-run |
— | — | Show the request that would be sent without executing it |
--draft |
— | — | Save as draft instead of sending |
Examples
gws gmail +send --to [email protected] --subject 'Hello' --body 'Hi Alice!'
gws gmail +send --to [email protected] --subject 'Hello' --body 'Hi!' --cc [email protected]
gws gmail +send --to [email protected] --subject 'Hello' --body '<b>Bold</b> text' --html
gws gmail +send --to [email protected] --subject 'Hello' --body 'Hi!' --from [email protected]
gws gmail +send --to [email protected] --subject 'Report' --body 'See attached' -a report.pdf
gws gmail +send --to [email protected] --subject 'Files' --body 'Two files' -a a.pdf -a b.csv
gws gmail +send --to [email protected] --subject 'Hello' --body 'Hi!' --draft
Tips
- Handles RFC 5322 formatting, MIME encoding, and base64 automatically.
- Use --from to send from a configured send-as alias instead of your primary address.
- Use -a/--attach to add file attachments. Can be specified multiple times. Total size limit: 25MB.
- With --html, use fragment tags (, , , , etc.) — no / wrapper needed.
- Use --draft to save the message as a draft instead of sending it immediately.
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.
- 1mo ago First seen · 68 lines · 13 tokens per session scan A 5002f29ed58e
gws-gmail-send is a skill published in the GitHub repository cblecker/claude-plugins (5 stars, last pushed 17d ago), licensed Apache-2.0. It adds 13 tokens to every session and 751 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to gws-gmail-send, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…