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.
npx skills add redhuntlabs/wizard --skill writing-an-emailgit clone --depth 1 https://github.com/redhuntlabs/wizardWrote 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.
[](https://agentmods.dev/skills/redhuntlabs/wizard/writing-an-email)<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.
<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>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 5.1 | $0.00023 | $0.00588 |
| Opus 5 | $0.00012 | $0.00294 |
| Sonnet 5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
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.
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)
- Identify the single goal: information / ask / acknowledgment.
- Write the subject line so it names the goal in 4-7 words.
- Open with one sentence that names the recipient-specific context.
- State the goal in one sentence.
- Add at most 2 supporting sentences.
- State the ask explicitly: what action, by when.
- 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
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.
- 9d ago First seen · 77 lines · 23 tokens per session scan A 2f84ac24752c
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.
Other skills, from other repositories
fastapi
A Python framework for building web APIs, which are interfaces that let programs communicate over HTTP. It supports request validation, automatic API documentation, asynchronous code, reusable dependencies, and common authentication methods.
glances
A guide for using Glances, a cross-platform system-monitoring tool that displays computer resource and process information in a terminal, browser, or API.
lazydocker
A keyboard-driven terminal interface for managing Docker, a system for running applications in isolated containers.
fzf
A command-line tool for finding items by typing partial text, with results updating as you type. It can search files, shell command history, processes, directories, Git branches, commits, and other text output.
paper-checking
A Windows application for finding copied text in documents. It compares files with a reference collection or compares documents in the same batch with one another.
you-get
A command-line tool for downloading videos, audio, and images from websites such as YouTube and Bilibili.