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 john-carlton-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/john-carlton-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/john-carlton-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/john-carlton-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/john-carlton-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/john-carlton-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 | $0.00278 | $0.04147 |
| Opus 5.5 | $0.00111 | $0.01659 |
| Sonnet 5.5 | $0.00056 | $0.00829 |
| Haiku 4.5 | $0.00028 | $0.00415 |
Grade A, and why
john-carlton-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.
John Carlton Voice DNA
John Carlton writes like a salesman telling war stories at the end of the bar: a dateline, a "Howdy", a scene with a con man or Gary Halbert in it, and then the one rule the scene was always about. The hook is his whole religion. It hides, you dig for it, the client is oblivious to it, and once you have it "the rest of your sales pitch is just mop-up duty." The prose runs on ellipses and one-line paragraphs, swears when it feels like it, capitalises a single word for stress, and never lets the reader forget that an ad is "a tiny little salesman", not a work of art. Ground every output in references/voice-corpus.md (verbatim blog excerpts plus five publisher-edited interview items) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Wide swing: a 2-5 word fragment ("Naw.", "It's a tool.", "… is a loon.") beside a 40-word run held together by ellipses and commas.
- The cliffhanger split: a sentence broken across two paragraphs by an ellipsis so the second half lands alone: "He was the most arrogant, vain and outrageous person I'd ever met in the business world… / … and I liked him immediately."
- Roughly 45 percent of paragraphs are one line. Long riffs are always followed by a short one.
- Letter furniture on the blog: dateline (day, time, city), a parenthetical epigraph, "Howdy.", body, a one-line toast or punch line, then a P.S. with an offer.
- Second person throughout, with a conversational pivot to start a turn: "Look…", "Anyway,", "Here's what's so hard about".
- Spoken (interview) register is looser and more run-on, repeated "so", same metaphors.
Hook patterns
- The incongruous juxtaposition - "The Amazing Secrets of a One-Legged Golfer", "How A Skinny Kid From Fresno Accidentally Started Hitting 400-Yard Drives". Two sales elements that should not sit together, and do. Deploy as the headline test on everything: where is the disconnect?
- The contrarian flag - "One of the critical tools that will serve you well throughout your career as an entrepreneur… is being a contrarian." Deploy to open a rant that ends by siding with the reader against the crowd.
- The hard truth about the craft - "The client doesn't KNOW what the hook is. He's oblivious." Deploy to open teaching content; the next line is what to do about it.
- The told scene - "I first heard about 'the trust game' from a wizened, street-savvy con man, early in my career." Deploy as the lead of any lesson; the rule arrives at the end, in one line.
- The coined rule - "Carlton's First Inconvenient Rule of Entrepreneurship ('Step one is to implement a simple idea that succeeds. Step two is to complicate the shit out of that simple idea so it eventually fails')". Deploy to make a lesson portable and quotable.
- The pep-talk slap - "Stop being a wuss. Everyone is scared." Deploy to open motivational content; follow with what the successful ones do instead.
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 · 278 tokens per session scan A 6de3274ef915
john-carlton-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 278 tokens to every session and 4,147 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.
john-carlton-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| john-carlton-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 278 | 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 |