compose-email

compose-email is a command for coding agents from jjmartres/ai-coding-agents. It costs 28 tokens per session (882 once invoked), scanned A, a copy of compose-email, MIT.

A command for drafting a professional email with a clear What-Why-How structure. It can tailor the message to the recipient, purpose, and urgency, or improve an existing draft.

In plain words
What is it for?
Writing status updates, requests, announcements, escalations, follow-ups, and other emails to developers, managers, customers, or mixed teams.
Why use it?
It reduces the effort of deciding what to say and how to organize technical information for different audiences.

Command

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/jjmartres/ai-coding-agents/compose-email
Clone the repo
git clone --depth 1 https://github.com/jjmartres/ai-coding-agents

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 compose-email

README.md
[![agentmods](https://agentmods.dev/badge/commands/jjmartres/ai-coding-agents/compose-email.svg)](https://agentmods.dev/commands/jjmartres/ai-coding-agents/compose-email)
Your own site
<a href="https://agentmods.dev/commands/jjmartres/ai-coding-agents/compose-email"><img src="https://agentmods.dev/badge/commands/jjmartres/ai-coding-agents/compose-email.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 882 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod 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 $0.00028 $0.00882
Opus 5 $0.00014 $0.00441
Sonnet 5 $0.00006 $0.00176
Haiku 4.5 $0.00003 $0.00088

Measured 3d ago against content hash da06546777e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compose-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 3d 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.

Origin

This is a copy

91% identical to compose-email — 2 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.

shared/.ai-agents/commands/compose-email.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft Professional Email

Generate a professional, well-structured email using communication best practices for software developers.

Arguments

$ARGUMENTS - Optional context, topic, or existing draft to refine

Workflow

Step 1: Gather Context

If $ARGUMENTS is empty or insufficient, use AskUserQuestion to gather:

Question 1: Recipient Type (header: "Audience")

  • Technical peer (developer, engineer)
  • Non-technical stakeholder (PM, executive, customer)
  • Cross-functional team (mixed audience)
  • Manager or leadership

Question 2: Email Purpose (header: "Purpose")

  • Status update or progress report
  • Request (review, approval, resources)
  • Information sharing (FYI, announcement)
  • Escalation or raising concern
  • Following up on prior conversation

Question 3: Urgency (header: "Urgency")

  • Urgent - needs response today
  • Standard - within 1-2 days
  • Low priority - for awareness only

Step 2: Apply Communication Framework

Use the What-Why-How structure:

  1. WHAT (Opening - 1-2 sentences)

    • Lead with the key message or request
    • State the purpose immediately
    • No throat-clearing ("I hope this email finds you well...")
  2. WHY (Context - 2-3 sentences)

    • Provide necessary background
    • Explain relevance to the recipient
    • Include only essential context
  3. HOW (Action - clear next steps)

    • Specific call-to-action
    • Clear deadline if applicable
    • Who needs to do what

Step 3: Apply Email Best Practices

Subject Line:

  • Specific and scannable (5-8 words ideal)
  • Include action needed: "[Action Required]", "[FYI]", "[Decision Needed]"
  • Include deadline if urgent: "[Due Friday]"

Body Structure:

  • Bullets for multiple points (3-5 max)
  • Bold key information
  • One topic per email
  • Short paragraphs (2-3 sentences max)

Tone Calibration by Audience:

Audience Tone Jargon Level
Technical peer Direct, precise High (use technical terms)
Non-technical Business-focused Low (translate jargon)
Cross-functional Balanced Medium (explain as needed)
Leadership Concise, impact-focused Low (focus on outcomes)

Read the full file on GitHub · 143 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. 3d ago First seen · 143 lines · 28 tokens per session scan A da06546777e7

Subscribe to this mod's changes

compose-email is a command published in the GitHub repository jjmartres/ai-coding-agents (43 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 882 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to compose-email, differing in 2 lines, and is treated as a copy.