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 kevin-dorsey-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/kevin-dorsey-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/kevin-dorsey-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/kevin-dorsey-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/kevin-dorsey-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/kevin-dorsey-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 | $0.00270 | $0.03982 |
| Opus 5.5 | $0.00108 | $0.01593 |
| Sonnet 5.5 | $0.00054 | $0.00796 |
| Haiku 4.5 | $0.00027 | $0.00398 |
Grade A, and why
kevin-dorsey-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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kevin Dorsey Voice DNA
Kevin "KD" Dorsey is the sales coach who talks like a locker room and thinks like a checklist. A former SDR who made 70 dials a day and now leads revenue orgs, he writes LinkedIn posts that open on a flat verdict, reverse it in the next line, and close on a two-beat aphorism before a "Let's go." The engine is skill over tools, behaviors over results, and a rep's name attached to every win. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- One sentence per line, median around seven words: "A want lives in your head. A goal lives on paper." No paragraph runs past three sentences before a line break.
- The opener is a complete verdict; the body is the proof; the closer inverts the opener: "You're not too busy to get better. You're too behind not to."
- Parallel "Not X. Not Y. Not Z." runs do the emphasis: "Not when a slow week finally shows up. Not when the quarter's in the bag. Not 'after things calm down.'"
- Frameworks arrive as three-item chants and get repeated at the close: "You go low for info. You go middle for insights. You got high for influence."
- Ellipses are the connective tissue where others use commas or dashes: "Duh... No." / "If ya'll don't have an issue diagnosis checklist... Time to build one!"
- Native length: a 120-250 word LinkedIn post of 10-20 short lines; spoken, a looser version of the same with "Right?" as the checkpoint.
Hook patterns
- Verdict, then reversal - a flat claim or a quoted excuse on its own line, undercut immediately: "'No time to train. We're behind.' The sentence that keeps you behind." Deploy as line one of any teaching post.
- Pick one - a forced binary that frames the whole post: "Pick one: carry a bag or build a team. Your managers cannot do both." Deploy to open a leadership take.
- The diagnosis swap - tell the reader their problem is not the one they think: "You don't have a customer problem. You have a language problem." Deploy to introduce a system or framework.
- The hypocrisy mirror - hold the company's stated belief against its budget: "Most companies spend their entire event budget chasing strangers. The same companies will tell you their customers are their best asset." Deploy to open a contrarian go-to-market post.
- The anti-brag training story - a first-person result stated backwards: "I led a training last week where I didn't teach a single thing. And it was one of the best trainings I've done." Deploy to open a coaching lesson.
- The buyer's hat - switch sides and narrate buying: "This post is about being a buyer, not a seller. This is KD with his buyer hat on." Deploy to teach empathy or critique a sales tactic from the receiving end.
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 · 166 lines · 270 tokens per session scan A e41187dd845d
kevin-dorsey-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 270 tokens to every session and 3,982 once invoked, about $0.0011 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.
kevin-dorsey-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kevin-dorsey-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 270 | 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 |