draft

An Outlook command that creates an email draft for review. Outlook is Microsoft's email service, and the command can draft a reply to an existing message or create a new message without sending it.

In plain words
What is it for?
Use it to find an email, understand its context, write a reply or new message, and place the result in Outlook Drafts.
Why use it?
It prepares the message while leaving the final review and sending decision to you.

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/muhammaddadu/outlook-cli/draft
Clone the repo
git clone --depth 1 https://github.com/muhammaddadu/outlook-cli
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 283 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 $0.00018 $0.00283
Opus 5 $0.00009 $0.00142
Sonnet 5 $0.00004 $0.00057
Haiku 4.5 $0.00002 $0.00028

Measured yesterday against content hash 4eca5cf759f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

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.

skill/commands/draft.md · 25 lines

What it actually says

The user invoked /draft with: $ARGUMENTS

Use the outlook CLI (skill: outlook) to create a draft the user can review in their Outlook Drafts folder before sending.

Workflow:

  1. If $ARGUMENTS references a specific email (sender, subject, keyword), run outlook search or outlook list to find its Id.
  2. Read the original with outlook read <id> to get context.
  3. Compose the reply body based on the user's instruction.
  4. Create the draft with outlook draft-reply <id> '{"Body": {"ContentType": "Text", "Content": "<body>"}}'.
  5. Return the DraftId and WebLink to the user. Tell them the draft is in their Drafts folder ready for review.

If the user wants a brand-new message (not a reply), use outlook draft with the full Message JSON.

Do not send mail directly via outlook send from this command — the whole point of /draft is the review step in Outlook.

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. yesterday First seen · 25 lines · 18 tokens per session scan A 4eca5cf759f6

Subscribe to this mod's changes

draft is a command published in the GitHub repository muhammaddadu/outlook-cli (2 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 283 once invoked, about $0.0001 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 2026-08-31.