writing-an-email

writing-an-email is a skill for Claude Code from redhuntlabs/wizard. It costs 23 tokens per session (588 once invoked), scanned A, original, MIT.

An email-drafting workflow for writing focused messages with a clear subject, context, purpose, ask, and sign-off.

In plain words
What is it for?
Use it for replies, outreach, requests, status updates, thank-you notes, and other emails. It helps produce a complete message with one clear goal.
Why use it?
It removes unnecessary padding and prevents messages from containing several unclear requests. It keeps routine emails short and centred on what the recipient should know or do.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the wizard plugin — 37 skills, 6 commands, 1 agent, 1 hook shipped together

Good fit Use it for replies, outreach, requests, status updates, thank-you notes, and other emails. It helps produce a complete message with one clear goal.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhuntlabs/wizard/writing-an-email
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.

Any agent
npx skills add redhuntlabs/wizard --skill writing-an-email
Clone the repo
git clone --depth 1 https://github.com/redhuntlabs/wizard

Made for: Claude Code.

Or install wizard, the plugin that ships this one along with the rest of its 37 skills, 6 commands, 1 agent, 1 hook.

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 writing-an-email

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhuntlabs/wizard/writing-an-email/github.svg)](https://agentmods.dev/skills/redhuntlabs/wizard/writing-an-email)
Your own site
<a href="https://agentmods.dev/skills/redhuntlabs/wizard/writing-an-email"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/writing-an-email/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.

agentmods 80×15 button for writing-an-email

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhuntlabs/wizard/writing-an-email"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/writing-an-email.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00023 $0.00588
Opus 5 $0.00012 $0.00294
Sonnet 5 $0.00005 $0.00118
Haiku 4.5 $0.00002 $0.00059

Measured 9d ago against content hash 2f84ac24752c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

writing-an-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 9d 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.

spells/everyday/writing-an-email/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing an Email

What this does

Drafts a focused email that opens with the point, has one ask, and ends without padding. Works for replies, cold outreach, status notes, asks, and thank-yous.

When to use

  • Drafting any new email
  • Replying to a long thread that needs a clear answer
  • Sending a request that has a specific ask

What you bring (Inputs)

  • Recipient name and one thing about them (role, prior context, shared connection)
  • The single thing you want them to do or know
  • Tone target (warm / neutral / formal — defaults to neutral)

What you get (Output)

A complete email: subject line, opener, body, ask, sign-off.

How it works (Steps)

  1. Identify the single goal: information / ask / acknowledgment.
  2. Write the subject line so it names the goal in 4-7 words.
  3. Open with one sentence that names the recipient-specific context.
  4. State the goal in one sentence.
  5. Add at most 2 supporting sentences.
  6. State the ask explicitly: what action, by when.
  7. Sign off without "I hope this finds you well" or apology.

Quality bar

  • Under 150 words for routine emails
  • One clear ask (or zero, if it's just info)
  • Subject line stands alone (recipient knows the topic without opening)
  • No opener filler ("Hope you're well", "Sorry for the delay")

Variations

  • Cold outreach: opener cites a specific recent thing about the recipient
  • Long-thread reply: open with one-sentence summary of the decision before details
  • Apology email: state what happened, what you're doing about it, what they can expect; no excuses
  • Thank-you: name the specific thing you're thanking for; no ask

Example

Input: Recipient: Sara, my manager. Goal: ask for headcount approval for one designer hire.

Output:

Subject: Headcount ask: 1 designer for Q3

Hi Sara,

Following our roadmap convo last Friday, I'd like to lock in one designer hire for Q3.

The case: shipping the new dashboard on time needs design ownership we don't have today. I've sourced 4 candidates already and can have an offer out by end of June.

Can you approve this by Friday so I can start interviews next week?

Thanks, Alex

Read the full file on GitHub · 77 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. 9d ago First seen · 77 lines · 23 tokens per session scan A 2f84ac24752c

Subscribe to this mod's changes

writing-an-email is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 588 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.