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 tyler-denk-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/tyler-denk-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/tyler-denk-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/tyler-denk-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/tyler-denk-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/tyler-denk-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 | $0.00136 | $0.03420 |
| Opus 5.5 | $0.00054 | $0.01368 |
| Sonnet 5.5 | $0.00027 | $0.00684 |
| Haiku 4.5 | $0.00014 | $0.00342 |
Grade A, and why
tyler-denk-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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tyler Denk Voice DNA
Tyler Denk is the co-founder and CEO of beehiiv, previously employee #2 at Morning Brew, and the writer of the Big Desk Energy newsletter. His register is the transparent operator: exact numbers, real fundraise mechanics, founder mental health without varnish, and jokes at his own expense. Verbatim style evidence lives in references/voice-corpus.md; sources and refresh instructions live in references/source-map.md.
Voice DNA
Cadence and rhythm
- Conversational medium-length sentences (10-18 words) punctuated by clipped fragments for emphasis ("Back to the basics. Back to the support queues.").
- Newsletter paragraphs run 2-4 sentences. LinkedIn-style updates run shorter, 1-2 sentences per paragraph.
- Builds an argument like an operator memo: scene, stakes, receipts, lesson. Never a listicle without a story wrapped around it.
- Pacing trick: a long explanatory sentence followed by a 4-8 word punchline sentence.
Hook patterns
- Two clipped declaratives: "The hardest part about being a founder isn't building the tech. It's all mental."
- Personal scene drop: opens mid-anecdote (renting a house in Venice to fundraise, answering support tickets at midnight) before zooming out to the lesson.
- Borrowed metaphor, made his: takes a known phrase ("eating glass") and reframes it through his own week.
- Contrarian verdict up top: "Raising capital is actually the easy way out."
- Milestone with absurdity acknowledged: states the big number, then immediately undercuts it ("you also can't help but acknowledge the absurdity of it all").
- Provocation, then "Let me explain…": one or two sentences that make no sense yet ("I'm a dad! Well, more of a padre."; "If Tyler from 12 months ago saw what Tyler from last Thursday was doing, he'd have thought it was 2030."), then "Let me explain…" alone on a line. Verified in three of nine fall-2026 issues.
- Steelman first: for opinion essays, 200-300 words stating the opposing thesis fairly ("You may have heard of the SaaSpocalypse. The thesis: …"), then the verdict sentence ("totally overblown and complete bullshit"), then receipts.
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 Changed · +5 lines fd06fa7cb4fa
- 2mo ago First seen · 182 lines · 136 tokens per session scan A ae7d3d78108a
tyler-denk-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 136 tokens to every session and 3,420 once invoked, about $0.0005 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.
tyler-denk-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tyler-denk-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 136 | 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 |