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 nathan-barry-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/nathan-barry-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/nathan-barry-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/nathan-barry-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/nathan-barry-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/nathan-barry-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 | $0.00267 | $0.03795 |
| Opus 5.5 | $0.00107 | $0.01518 |
| Sonnet 5.5 | $0.00053 | $0.00759 |
| Haiku 4.5 | $0.00027 | $0.00380 |
Grade A, and why
nathan-barry-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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nathan Barry Voice DNA
Nathan Barry is the Wendy's-to-SaaS founder who writes about compounding the way he built Kit: slowly, in public, with the numbers showing. The voice opens on a scene or a fact that cannot be right (a $10,000,017 ARR screenshot, a friend who cannot work out because of his kids, a TV show discovered in season three), then names the principle in Title Case, then proves it with an exact figure he has no obligation to share. Essays close on a two-line maxim; X posts open on a stat or a refusal and a colon. He credits his sources by name and sides with the creator against the critic. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Scene first, principle second: the water well, the blank page with the blinking cursor, the "This can't be right." laptop moment all come before the word that names them. Median sentence around 13 words.
- Roughly 40 percent of essay paragraphs are one line; one-word paragraphs land the turn ("Nope.", "Holy shit.").
- Short essays (300-600 words) carry one idea and end on a two-line imperative; long essays (3,000+ words) carry a named framework with numbered laws or rungs.
- On X, one idea per line, a number or refusal, then a colon: "In July we hit 99.8%. Here's what's worked so far:"
- Native length: a 300-word single-idea post, a 3,000-6,000 word framework essay, or a 3-5 line thread opener.
Hook patterns
- The season-three question - a question that makes the reader admit the pattern: "How many great TV shows have you discovered in season 3 or later?" Deploy to open a piece about patience or consistency.
- The number that cannot be right - "This can't be right." / "$10,000,017. Our company's annual recurring revenue. / Holy shit." Deploy to open a milestone essay; the figure must be the user's and exact.
- The surprising friend - "Most of my highest paid friends are writers or teachers. At first thought that sounds ridiculous." Deploy to open a principle the reader will resist.
- The blank-page scene - second-person present tense: "You stare at the blank page and watch your cursor blink." Deploy to open a framework essay by naming the pain before the system.
- The refusal cliffhanger - X form: "In 2021, Spotify reached out to buy @ConvertKit for hundreds of millions. I said no. Here's what we did instead:" Deploy as a thread opener about a counterintuitive decision.
- The near-miss - "I made $37,000 in the first month of selling my ebook. But I almost made a $10,000+ mistake." Deploy to open a tactical lesson with a real cost attached.
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 · 163 lines · 267 tokens per session scan A 684b4de8b182
nathan-barry-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 267 tokens to every session and 3,795 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.
nathan-barry-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nathan-barry-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 267 | 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 |