persona-style-transfer

persona-style-transfer is a skill for Claude Code from sumitaich1998/OpenDate. It costs 38 tokens per session (622 once invoked), scanned A, original, MIT.

A final editing step that rewrites a drafted message to match the user’s usual voice, including word choice, tone, punctuation, message length, and humor.

In plain words
What is it for?
It is for adapting messages to a persona profile after another process has drafted them, including matching slang, emojis, cadence, openers, and closers.
Why use it?
It helps prevent a message from sounding unlike the person who is meant to send it while keeping its meaning and intent unchanged.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Good fit It is for adapting messages to a persona profile after another process has drafted them, including matching slang, emojis, cadence, openers, and closers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sumitaich1998/opendate/persona-style-transfer
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 sumitaich1998/OpenDate --skill persona-style-transfer
Clone the repo
git clone --depth 1 https://github.com/sumitaich1998/OpenDate

Made for: Claude Code.

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 persona-style-transfer

README.md
[![agentmods](https://agentmods.dev/badge/skills/sumitaich1998/opendate/persona-style-transfer/github.svg)](https://agentmods.dev/skills/sumitaich1998/opendate/persona-style-transfer)
Your own site
<a href="https://agentmods.dev/skills/sumitaich1998/opendate/persona-style-transfer"><img src="https://agentmods.dev/badge/skills/sumitaich1998/opendate/persona-style-transfer/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 persona-style-transfer

Your own site · 80×15
<a href="https://agentmods.dev/skills/sumitaich1998/opendate/persona-style-transfer"><img src="https://agentmods.dev/badge/skills/sumitaich1998/opendate/persona-style-transfer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 622 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 $0.00038 $0.00622
Opus 5 $0.00019 $0.00311
Sonnet 5 $0.00008 $0.00124
Haiku 4.5 $0.00004 $0.00062

Measured 11d ago against content hash 6f032e939b26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

persona-style-transfer 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 11d 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.

src/opendate/skills/registry/persona-style-transfer/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persona style transfer

This is the final pass on every outgoing message. Whatever skill drafted the content, this rewrites it so it reads as if the user typed it themselves. The meaning and intent stay identical; the voice becomes theirs.

Inputs

You receive:

  • The draft (from the primary skill).
  • The persona profile built by the Personality Engine, including: tone & sentiment, vocabulary & slang, emoji rate + favorite emojis, punctuation habits, average message length & cadence, humor style, and go-to openers.

What to match

  1. Tone & sentiment — warm vs dry, earnest vs sarcastic, hyped vs measured.
  2. Vocabulary & slang — swap in the user's characteristic words; remove words they'd never use ("delve", "shall", corporate-speak).
  3. Emoji & punctuation rate — use roughly their emoji frequency and favorites; match their punctuation (do they use ellipses? lowercase? em-dashes? "lol"?).
  4. Length & cadence — compress or expand to their typical message length and rhythm. Many people text in short bursts.
  5. Humor style — dry, goofy, pun-heavy, deadpan, wholesome — match it.
  6. Openers/closers — favor their habitual phrasings where natural.

Rules

  • Preserve meaning and intent exactly. Don't add claims, change the ask, or invent facts about the user. Style only.
  • Don't fabricate biography. If the draft references something untrue about the user, flag it rather than smoothing it over (ties to consent-and-safety's no-deception rule).
  • Keep it natural, not a caricature. Match habits; don't cram in every slang word and emoji at once.
  • Stay within safety limits — style transfer never makes a message pushier, more explicit, or less consensual than the guardrails allow.
  • Degrade gracefully. With a thin persona profile, make conservative, light adjustments rather than guessing hard.

Process

  1. Read the draft's intent.
  2. Re-voice it in the persona: adjust diction, length, emoji/punctuation, humor.
  3. Sanity-check meaning is unchanged and nothing untrue was introduced.
  4. Return only the final message text.

Read the full file on GitHub · 60 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. 11d ago First seen · 60 lines · 38 tokens per session scan A 6f032e939b26

Subscribe to this mod's changes

persona-style-transfer is a skill published in the GitHub repository sumitaich1998/OpenDate (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 622 once invoked, about $0.0002 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.