reply-in-your-voice

reply-in-your-voice is a skill for Claude Code from Ootto-AI/claude-inbox-skills. It costs 69 tokens per session (499 once invoked), scanned A, original, MIT.

An email-reply drafting helper that studies two or three of your past emails and uses them as examples of your writing style.

In plain words
What is it for?
Drafting replies to emails in your usual tone, including matching your greetings, sign-offs, sentence length, and formatting.
Why use it?
It avoids replies that sound too formal, too casual, or unlike you. You still provide the message and what you want to say.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the claude-inbox-skills plugin — 5 skills shipped together

Good fit Drafting replies to emails in your usual tone, including matching your greetings, sign-offs, sentence length, and formatting.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ootto-ai/claude-inbox-skills/reply-in-your-voice
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 Ootto-AI/claude-inbox-skills --skill reply-in-your-voice
Clone the repo
git clone --depth 1 https://github.com/Ootto-AI/claude-inbox-skills

Made for: Claude Code.

Or install claude-inbox-skills, the plugin that ships this one along with the rest of its 5 skills.

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 reply-in-your-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/ootto-ai/claude-inbox-skills/reply-in-your-voice/github.svg)](https://agentmods.dev/skills/ootto-ai/claude-inbox-skills/reply-in-your-voice)
Your own site
<a href="https://agentmods.dev/skills/ootto-ai/claude-inbox-skills/reply-in-your-voice"><img src="https://agentmods.dev/badge/skills/ootto-ai/claude-inbox-skills/reply-in-your-voice/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 reply-in-your-voice

Your own site · 80×15
<a href="https://agentmods.dev/skills/ootto-ai/claude-inbox-skills/reply-in-your-voice"><img src="https://agentmods.dev/badge/skills/ootto-ai/claude-inbox-skills/reply-in-your-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 499 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 $0.00069 $0.00499
Opus 5 $0.00034 $0.00249
Sonnet 5 $0.00014 $0.00100
Haiku 4.5 $0.00007 $0.00050

Measured 12d ago against content hash 7a4aaae1a4d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reply-in-your-voice 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 12d 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/reply-in-your-voice/SKILL.md · 51 lines

What it actually says

Reply in Your Voice

Draft a reply to any message that sounds like you.

When to use

You need to answer an email and want the draft to sound like you wrote it — not more corporate or more casual than you actually are.

What you'll need

The message you're replying to, plus 2-3 emails you've actually written before (so Claude can learn your voice).

Instructions

Collect any missing inputs from the user, then run this prompt:

You are writing an email reply in my voice. First, study how I write from these samples of my own past emails:

[paste 2-3 emails you've written]

Notice my tone, sentence length, greeting and sign-off, level of formality, and whether I use things like dashes, lists, or short paragraphs. Match it — don't make me sound more corporate or more casual than I am.

Now write a reply to this message:

[paste the email you're replying to]

What I want to get across: [say in plain words what you want to say — e.g. "yes but push the call to Thursday", "no thanks, not a fit right now"]

Write the reply so it sounds like I wrote it. Keep it as short as the situation allows. Don't add greetings or closings I wouldn't use. Give me just the reply text, ready to paste.

Tip: The quality is almost entirely in the writing samples. Pick emails where you sound the most like yourself — a quick one to a colleague beats a polished one to a client.


Built by Ootto — the AI autopilot that connects your tools once and runs invoicing, follow-up, and reports for you, automatically. Book a demo →

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. 12d ago First seen · 51 lines · 69 tokens per session scan A 7a4aaae1a4d3

Subscribe to this mod's changes

reply-in-your-voice is a skill published in the GitHub repository Ootto-AI/claude-inbox-skills (1 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 499 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

guest-outreach-email

Writes a personalized outreach email inviting a specific person to appear as a guest on a podcast episode, with a clear pitch for why this conversation would be valuable to them and their audience.

ur-grue/autopunk-media-skills · 41 tokens

newsletter-teaser-writer

Writes a short, high-click newsletter teaser for a published article — including subject line options, preview text, and the teaser body — ready to paste into an email newsletter platform.

ur-grue/autopunk-media-skills · 41 tokens

cold-outreach-email-writer

Writes a cold outreach email to a broadcaster, distributor, or platform executive introducing a project for the first time and requesting a meeting or a read of supporting materials.

ur-grue/autopunk-media-skills · 39 tokens

follow-up-email-writer

Writes a professional follow-up email to a journalist, editor, or media contact who has not responded to a previous pitch or request, calibrated to the relationship stage, urgency, and number of prior attempts.

ur-grue/autopunk-media-skills · 46 tokens

thank-you-email-writer

Writes a brief, genuine thank-you email to a journalist or media contact after coverage, an interview, or a professional favour, reinforcing the relationship without being transactional.

ur-grue/autopunk-media-skills · 38 tokens

watch-video

Give Claude eyes and ears on any online video, then analyze it. Downloads a video from a URL (YouTube, Instagram, X, Vimeo, and 1000+ yt-dlp sites), extracts key frames, and gets a transcript (native captions, else local Whisper), then hands the frames + timestamped transcript to Claude so it can produce a full…

Ootto-AI/ootto-watch · 149 tokens