kevin-voice

kevin-voice is a skill for Claude Code, Codex from Kevin-Liu-01/Agent-Machines. It costs 137 tokens per session (2,258 once invoked), scanned A, original, MIT.

A writing style guide for describing Kevin Liu in third person, using concise fragments focused on verified credentials and experience.

In plain words
What is it for?
Use it to write recruiter blurbs, LinkedIn sections, conference bios, introductions, outreach openers, and spoken interview answers.
Why use it?
It keeps bios, profiles, and introductions consistent and prevents unsupported claims about Kevin's work or background.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to write recruiter blurbs, LinkedIn sections, conference bios, introductions, outreach openers, and spoken interview answers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kevin-liu-01/agent-machines/kevin-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 Kevin-Liu-01/Agent-Machines --skill kevin-voice
Clone the repo
git clone --depth 1 https://github.com/Kevin-Liu-01/Agent-Machines

Made for: Claude Code, Codex.

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 kevin-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/kevin-voice/github.svg)](https://agentmods.dev/skills/kevin-liu-01/agent-machines/kevin-voice)
Your own site
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/kevin-voice"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/kevin-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 kevin-voice

Your own site · 80×15
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/kevin-voice"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/kevin-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,258 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 32
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00137 $0.02258
Opus 5 $0.00068 $0.01129
Sonnet 5 $0.00027 $0.00452
Haiku 4.5 $0.00014 $0.00226

Measured 9d ago against content hash e0e91a596775, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

kevin-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 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.

knowledge/skills/kevin-voice/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kevin Voice

Kevin's third-person positioning voice. Modeled on the credential-forward "Why?" blurbs Sequoia / curated job platforms generate for him. Compresses real proof points from the wiki into sentence fragments that earn the reader's attention without sounding like a cover letter.

Scope: self-positioning only. Bios, blurbs, headlines, openers, About sections. Also use for spoken interview answers when Kevin needs to sound like himself out loud, not like a written profile.

  • For social posts in Kevin's voice → social-draft
  • For generic marketing copy → copywriting
  • For job evaluation / CV tailoring → career-ops

Source of Truth (read every time)

Before writing anything, load these wiki pages. Never invent a fact, company, metric, or title. If the proof isn't here, ask Kevin or use a different angle.

File What it has
wiki/USER.md Identity, current work, strengths, key people
wiki/career/career-profile.md Positioning, target roles, differentiators, LinkedIn strategy
wiki/career/resume.md Companies, dates, bullets, metrics, publications

If any of these are stale or missing, run npx tsx scripts/check-freshness.ts and surface the gap before writing.

The Core Pattern (Why? blurb)

[CREDENTIAL NOUN] [optional CONTEXT TAG] with [PROOF NOUNS]

Examples that actually appear in his recruiting feed:

  • "Founding engineer with full-stack and AI infrastructure proven"
  • "Founding engineer at ideal YC company with agentic expertise"
  • "Princeton CS founding engineer with infrastructure and systems experience"
  • "Founding engineer with 0-to-1 shipping and full-stack capabilities"

Anatomy:

  • Credential noun (lead): Founding engineer, Princeton CS founding engineer, YC founding engineer, Bloomberg + AWS engineer, Agent infrastructure engineer. Strongest single noun phrase first.
  • Context tag (optional): at YC AI company, at agent infrastructure startup. Only add when it sharpens the fit for the audience.
  • Proof nouns (the differentiation): comma- or and-joined nouns derived from real shipped work. agentic expertise, 0-to-1 shipping, multi-tenant auth, MCP-powered SDK, customer delivery experience.
  • Length: 10–22 words.
  • Person: third-person fragment. No "I", no verb-led sentence.

Read the full file on GitHub · 201 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 · 201 lines · 137 tokens per session scan A e0e91a596775

Subscribe to this mod's changes

kevin-voice is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed today), licensed MIT. It adds 137 tokens to every session and 2,258 once invoked, about $0.0007 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 2026-09-03.

Related

Other skills, from other repositories