A command for sending email directly from a terminal, including recipients, copies, blind copies, and attachments. It validates addresses and checks input before invoking the email helper.

Use it to send an email from the command line with To, CC, BCC, and attachment details.

It avoids switching to a separate mail application while adding safeguards against malformed addresses and unsafe command input.

send — Command by ThrownLemon

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 commands/thrownlemon/claude-code-plugins/send

Clone the repo

git clone --depth 1 https://github.com/ThrownLemon/claude-code-plugins

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,010 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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	$0.00008	$0.01010
Opus 5	$0.00004	$0.00505
Sonnet 5	$0.00002	$0.00202
Haiku 4.5	$0.00001	$0.00101

Measured yesterday against content hash 018ab4c5c468, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

send scanned grade C with 1 finding 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 yesterday.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. **Reject dangerous tokens.** If a value contains `$(`, backticks, `;`, `|`, `&`, `>`, `<`, or starts with `-` (could be mistaken for a flag), refuse and ask the user to rephrase. **Double-quoting does NOT block comman

plugins/gmcli/commands/send.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Input Safety — apply before any Bash invocation

Treat every $ARGUMENTS.* value as untrusted input. Before passing any value to the Bash tool:

Reject dangerous tokens. If a value contains $(, backticks, ;, |, &, >, <, or starts with - (could be mistaken for a flag), refuse and ask the user to rephrase. Double-quoting does NOT block command substitution — "$(rm -rf /)" still executes inside double quotes.
Prefer the Bash tool's argv contract over constructed shell strings. When you must use a shell string, single-quote the value and escape embedded single quotes ('\''), or build the command via printf %q.
Any "$ARGUMENTS.foo" patterns shown below are illustrative. Sanitize the value first; never blindly substitute.

Send Email

Send an email directly from the terminal with full support for CC, BCC, and attachments.

What This Does

This command delegates to the gmail-assistant subagent which will:

Validate Input
- Verify to, cc, and bcc values match the pattern [^@\s]+@[^@\s]+\.[^@\s]+ — reject any address that does not match and ask the user to correct it before proceeding.
- Reject any address value containing shell metacharacters ($(, backticks, ;, |, &, >, <).
- Verify attachments exist on disk before sending.
- Confirm the sending account is authenticated.
Compose Email
- Format message with provided details.
- Pass -- before user-supplied positional arguments to prevent flag injection (e.g., gmcli send -- --to ...).
- Attach files if specified.
Confirm Before Sending
- Always show a confirmation prompt before sending:
  About to send:
  - To: <to>
  - Subject: <subject>
  - Body preview: first 100 chars…
  - Attachments: <files or none>
  Proceed? (yes / no)
- Do not send until the user explicitly confirms.
Send and Report
- Execute send via gmcli.
- Report success/failure and show sent message details.

Read the full file on GitHub · 109 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.

yesterday First seen · 109 lines · 0 tokens per session scan C 018ab4c5c468

Subscribe to this mod's changes

send is a command published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 1,010 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Productivity

send

Getting it into your agent

What it costs to keep this loaded

Grade C, and why

Recursive force deletehighDestructive command

How it starts

Input Safety — apply before any Bash invocation

Send Email

What This Does

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement