send-email

send-email is a skill for Claude Code, Codex from Darwin-Agent/Car-bench-TRACE. It costs 0 tokens per session (3,651 once invoked), scanned A, original, MIT.

An email-sending workflow that drafts a message, resolves the recipient from saved contact details, asks for confirmation, and sends only after an explicit yes.

In plain words
What is it for?
Use it to send requested details, trip plans, or meeting-weather updates after the recipient and message contents are settled.
Why use it?
It prevents messages from being sent prematurely and avoids guessing a recipient's email address or unresolved content.

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/darwin-agent/car-bench-trace/send-email
Any agent
npx skills add Darwin-Agent/Car-bench-TRACE --skill send-email
Clone the repo
git clone --depth 1 https://github.com/Darwin-Agent/Car-bench-TRACE

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.

agentmods badge for send-email

README.md
[![agentmods](https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/send-email.svg)](https://agentmods.dev/skills/darwin-agent/car-bench-trace/send-email)
Your own site
<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/send-email"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/send-email.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,651 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 $0.00000 $0.03651
Opus 5 $0.00000 $0.01826
Sonnet 5 $0.00000 $0.00730
Haiku 4.5 $0.00000 $0.00365

Measured 5d ago against content hash 77ad4455e016, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

send-email 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.

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.

skills_bank/send-email/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compose and send an email (only after confirmation)

The user wants an email sent — contact details to someone, an EV trip plan, a weather update for a meeting. You draft it, confirm, and send only on an explicit "yes". The recipient's address comes from a real resolved contact, never invented, and when more than one contact could be the recipient you ask which one. The body contains only what the user asked for or what has been settled with them — you do not invent the trip's decisions, charging plan, or numbers on their behalf. The one variant that adds a tool here is a meeting-weather update, where the body needs a weather read. Resolving the recipient/contacts is the contacts-lookup skill; this skill composes and sends.

When this applies

"Email the details", "send the trip plan", "email someone from my the forecast for where we're meeting." The deliverable is a sent email; the recipient and any looked-up content have already been (or are being) resolved by contacts-lookup.

Tools

  • send_email({email_addresses, content_message}) — send the message. Recipient address(es) come from the resolved contact's own details. The send validates each address against saved contacts: an address the user types that isn't on a contact can be rejected, and you have no tool to add or edit contacts — so don't promise to "add it" and don't fabricate. May be the removed tool.
  • get_user_preferences({preference_categories:{productivity_and_communication:{email:true}}}) — read the user's standing email preferences. Check this before sending: a stored preference can name a person to always copy (such as a secretary) or otherwise shape the recipient list. A standing recipient lives here, not in the request, so it only surfaces if you read it.
  • get_weather({month, day, time_hour_24hformat, location_or_poi_id}) — read the weather for a meeting's place around the meeting time, when the body is a weather update.
  • get_location_id_by_location_name({location}) — resolve a meeting's location to an id so the weather query can run.

Read the full file on GitHub · 82 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. 5d ago First seen · 82 lines · 0 tokens per session scan A 77ad4455e016

Subscribe to this mod's changes

send-email is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (7 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,651 tokens. 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 2026-08-31.