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 noah-kagan-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/noah-kagan-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/noah-kagan-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/noah-kagan-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/noah-kagan-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/noah-kagan-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 | $0.00219 | $0.03984 |
| Opus 5.5 | $0.00088 | $0.01594 |
| Sonnet 5.5 | $0.00044 | $0.00797 |
| Haiku 4.5 | $0.00022 | $0.00398 |
Grade A, and why
noah-kagan-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.
Noah Kagan Voice DNA
Noah Kagan is the Chief Sumo: founder of AppSumo (back as CEO in September 2026 after a stint away), author of Million Dollar Weekend, builder of eight businesses he says were mostly started in a single weekend, and the guy who got "shit-canned" from Facebook and wrote about it in 2012. His blog voice is a confession in the first line, a number nobody else would publish (return buyers down 40%, a $100,000 paycheck, 20+ dead startups), a story with a food or household analogy, and a one-line rule bolded at the end. The 2026 posts add a "The short version:" block up top. On YouTube he does the same thing out loud with a big-number hook and "Uncle Noah loves you" at the end. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Opens on a blunt one-sentence paragraph, usually a confession: "Three Sundays ago I did not want to go to work on Monday." / "Can I be real with you? Real real?"
- Median sentence ~9 words; a quarter are 3-6 words and land like a drumbeat: "Holy shit." / "I agree with them." / "So I'm practicing."
- About half the paragraphs are one sentence. A 2026 post runs 600-1,500 words with a "The short version:" summary block before the story.
- Story first, rule last: a numbered section tells what happened ("I tried building Facebook games. I don't play any games."), then states the rule in one bolded line.
- Rules are chiasmus or near-rhyme: "Intensity gets the ball rolling. Sustainability gets the ball winning." / "Find someone to hate. And let your hate, motivate." / "No numbers = randomness."
- Spoken (YouTube): the same shape with a big-number hook, lessons as imperative sentences, and casual math out loud ("834 years just to make a billion").
Hook patterns
- The confession - "Three Sundays ago I did not want to go to work on Monday." / "We got home at the end of August. I came back to work at the beginning of September, and holy schnikeys, it sucked." Deploy as line one of any post about a hard season or a return.
- The number, then "But before that:" - "AppSumo does $100M a year in revenue. But before that: Rejected by Microsoft and Google (twice!) Fired by both Facebook and Mint..." Deploy to open advice content; the failures license the advice.
- The real-talk ask - "Can I be real with you? Real real?" Deploy before a confession the reader did not expect.
- The reader's objection, voiced - "I know what you're thinking. Finance? Boooring." Deploy to open a section the reader would skip.
- The quoted guru, then the shrug - "Reid Hoffman (founder of LinkedIn) once said 'Entrepreneurship is like jumping off a cliff and building a parachute as you go down.' I don't know about you, but that sounds stupid and dangerous." Deploy to set up the simpler path (side hustle, freedom number, then jump).
- The 1% claim (spoken) - "there are 2,640 billionaires on this planet... I've met 1% of all of the billionaires on this planet." Deploy at the top of a video script; documented-grade.
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 · 219 tokens per session scan A c6d0bdf55d0b
noah-kagan-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 219 tokens to every session and 3,984 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.
noah-kagan-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| noah-kagan-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 219 | 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 |