agentmods.dev

mark-cuban-voice

mark-cuban-voice is a skill for Claude Code from jpeslar1/john-peslar-ai-skills. It costs 111 tokens per session (2,550 once invoked), scanned A, original, MIT.

A writing guide modeled on the public speaking and writing style associated with Mark Cuban, entrepreneur and investor. It focuses on fast, conversational language about effort, sales, competition, and knowing a business well.

In plain words
What is it for?
Use it to draft social posts, interview-style answers, objection responses, contrarian opinions, and sales or business advice in that public style.
Why use it?
It gives structure to direct, forceful writing without needing to imitate private speech or knowledge. It helps make arguments sound practical and decisive.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the voice-dna plugin — 79 skills shipped together

not rated 12repo +1 changed 18d ago A scan 111 tokens original MIT

Good fit Use it to draft social posts, interview-style answers, objection responses, contrarian opinions, and sales or business advice in that public style.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jpeslar1/john-peslar-ai-skills/mark-cuban-voice
View source ↗ jpeslar1/john-peslar-ai-skills
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 jpeslar1/john-peslar-ai-skills --skill mark-cuban-voice
Clone the repo
git clone --depth 1 https://github.com/jpeslar1/john-peslar-ai-skills

Made for: Claude Code.

Or install voice-dna, the plugin that ships this one along with the rest of its 79 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 mark-cuban-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/mark-cuban-voice/github.svg)](https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/mark-cuban-voice)
Your own site
<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/mark-cuban-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/mark-cuban-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 mark-cuban-voice

Your own site · 80×15
<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/mark-cuban-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/mark-cuban-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,550 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 $0.00111 $0.02550
Opus 5.5 $0.00044 $0.01020
Sonnet 5.5 $0.00022 $0.00510
Haiku 4.5 $0.00011 $0.00255

Measured 18d ago against content hash 8fef51dd5971, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mark-cuban-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.

mark-cuban-voice/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mark Cuban Voice DNA

Mark Cuban is a serial founder (MicroSolutions, Broadcast.com, Cost Plus Drugs), longtime Shark Tank investor, and former Dallas Mavericks owner. His register is rapid, conversational, combative when challenged, and relentlessly about effort, sales, and knowing your business cold. He is X and interview native: he types like he talks, does not format for platforms, and picks fights with entire industries. Ground every output in references/voice-corpus.md and references/source-map.md.

Voice DNA

Cadence and rhythm

  • Spoken-rhythm sentences, 6-18 words, often chained with "and" like live speech.
  • Paragraphs short and unpolished. On X he writes replies, not essays: 1-3 sentences, lowercase-tolerant, fired fast.
  • Momentum builds by repetition: "I want to kill the competitors. I want to make their lives miserable. I want to steal their market share."
  • Interview mode allows longer runs but always lands on a hard practical point.

Hook patterns

  1. The effort gauntlet - success framed as outworking everyone, stated as a threat. "Work like there is someone working 24 hours a day to take it all away from you."
  2. The one-time truth - failure count doesn't matter. "You only have to be right once."
  3. The blunt diagnosis - names the real problem in a sentence, usually effort or sales. "Sales cures all."
  4. The industry callout - picks a fight with a whole sector (PBMs, banks, crypto grifters) on behalf of the little guy.
  5. The anti-glamour story - mustard-and-ketchup-sandwiches era proof that he lived the grind before preaching it.
  6. The control frame - the only variable you own is effort. "One thing we can all control is effort."

Lexicon

  • Signature words: effort, hustle, sales, sweat equity, edge, obsession, brainpower, grind, "get off your ass", "know your business better than anyone".
  • Register: locker-room plain talk. Comfortable with mild profanity in speech and in his own blog ("What a bunch of BS", "kick your ass"). Zero MBA-speak, zero buzzwords.
  • Pet phrases verified in his own typing (2026-10-18): "How cool is that.", "There are no shortcuts.", "Do the work.", "the sport of business", "Eat Your Lunch", "show me a plan" (2026 healthcare posts). Opener habit: a rhetorical question he answers himself ("Does anybody here like their health care? ... That's why.").
  • Not his: "Business is war. I want to kill the competitors." That line was found in no primary source and duplicates another voice's corpus; do not use it in his name.
  • Numbers used as receipts (units sold, margins, drug prices), not as decoration.

Read the full file on GitHub · 179 lines

Files

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.

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. 18d ago Changed · +2 lines 8fef51dd5971
  2. 2mo ago First seen · 177 lines · 111 tokens per session scan A f0db3988e2ba

Subscribe to this mod's changes

mark-cuban-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 111 tokens to every session and 2,550 once invoked, about $0.0004 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 2026-08-31.

Marketing and SEOWriting and docs
Related

mark-cuban-voice compared with skills from other repositories

mark-cuban-voice next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mark-cuban-voicejpeslar1/john-peslar-ai-skillsSkill1218d agoMITA111Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code