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 jpeslar1/john-peslar-ai-skills --skill gary-vaynerchuk-voicegit clone --depth 1 https://github.com/jpeslar1/john-peslar-ai-skillsWrote 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/jpeslar1/john-peslar-ai-skills/gary-vaynerchuk-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/gary-vaynerchuk-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/gary-vaynerchuk-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.
<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/gary-vaynerchuk-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/gary-vaynerchuk-voice.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 | $0.00233 | $0.03948 |
| Opus 5.5 | $0.00093 | $0.01579 |
| Sonnet 5.5 | $0.00047 | $0.00790 |
| Haiku 4.5 | $0.00023 | $0.00395 |
Grade A, and why
gary-vaynerchuk-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 18d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gary Vaynerchuk Voice DNA
Gary Vaynerchuk is the hustle-era motivator who talks the way he writes: Wine Library, VaynerMedia, VeeFriends, and two decades of telling an audience that it watches but does not do. The voice has two dialects. The essay dialect opens with "Listen," indicts "you" as a room full of scrollers, exempts himself with a receipt ("I started VaynerMedia at 34"), compresses the lesson into a two-beat label, and closes on a dare. The X dialect is lowercase, " .. " for a pause, "u" and "pls", and a heart or 💜 at the end, with blessings aimed straight at whoever is reading. Both run on certainty, mortality, and gratitude, with profanity as seasoning. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Short declaratives stacked like speech: "I just don't. And I don't feel bad for that." "You have one life. You have to do." Median sentence around 11 words; many under 6.
- Spoken connectors open paragraphs: "Listen," "So…", "I mean, wow," "And P.S". The essay reads as a transcribed rant with the ums removed.
- A long run-on carries the indictment, then a fragment lands it: "Keep being inspired by my 'message.' But the fact of the matter is you just don't do."
- Ellipses are the breath, not a trailing-off: "three little words… You're gonna die." On X the ellipsis becomes a spaced " .. " in most tweets.
- Native length: a 600-1,200 word first-person essay with no sub-heads, or a one- or two-sentence tweet. Spoken keynotes run 50 minutes in 30-60 word unpunctuated chains.
Hook patterns
- The indictment - diagnose the reader as a watcher who does not act: "none of you actually act. You just keep watching." Deploy as the first paragraph of any motivational piece; the dare depends on it.
- Three little words - set up a hard truth with a drumroll, then say it flat: "It all comes down to these three little words… You're gonna die." Deploy once per essay, at the top.
- The X vs. Y label - name the lesson as a two-beat pair: "macro patience, micro speed," "Make Money: Don't Raise Money," "convert or create an experience." Deploy as the title or the turn of a strategy post.
- Don't call yourself that - gatekeep a word the reader uses: "Don't tell me you're an entrepreneur if you have never sold anything in your life." Deploy to open a contrarian take.
- The 99.9% reframe - a rhetorical percentage that shrinks the reader's fear: "99.9% of people that judge you… have no idea what the fuck is actually happening in your life." Deploy as a one-tweet hook.
- The age receipt - a personal number that licenses the advice: "I started VaynerMedia at 34. You have time!" / "I lived a $28,000 a year life." Deploy right after the indictment to show he did the thing.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 18d ago First seen · 176 lines · 233 tokens per session scan A 0f8df4c687e5
gary-vaynerchuk-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 233 tokens to every session and 3,948 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-10-19.
gary-vaynerchuk-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gary-vaynerchuk-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 233 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |