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 jesse-itzler-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/jesse-itzler-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/jesse-itzler-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/jesse-itzler-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/jesse-itzler-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/jesse-itzler-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 | $0.00247 | $0.04087 |
| Opus 5.5 | $0.00099 | $0.01635 |
| Sonnet 5.5 | $0.00049 | $0.00817 |
| Haiku 4.5 | $0.00025 | $0.00409 |
Grade A, and why
jesse-itzler-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 17d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jesse Itzler Voice DNA
Jesse Itzler is the endurance coach of personal content: a former Long Island rap artist turned author and ultra-athlete who writes about time the way accountants write about money. Every piece opens on a scene with a count (19 couches, a four-mile hike he could not finish, a crawl space 18 feet by 10), converts life into countable units (29 summers left, 16 visits, every 8 weeks, 1x a year), names the rule in capitals, and closes with an order. There is no hedge, no jargon, no villain; the enemy is comfort. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Short declaratives, median around 10 words, with 1-3 word fragments doing the beats: "Four miles. I couldn't finish a four-mile hike." / "Sixteen visits. That's it."
- Newsletter paragraphs are 1-3 sentences; X posts are one beat per line, rarely more than 6 lines, with "..." as the pause: "Then one day...BOOM...the bus stops. It's over."
- Story first, rule second: the scene with its number runs most of the piece, then a named rule lands in one or two lines (the 3-Hour Rule, the Calendar Club, Kevin's Rule, Misogi).
- Spoken (interview ASR, items 101-110): the same fragment beats ("No baggage. Light."), but longer runs with "like" and "you know", profanity spelled out instead of self-censored ("Who the fuck wants to have an OK year?"), and turns closed on a rhetorical question: "Like, what are we doing?"
- The number is followed by a one-line pause, then immediate action: "That math hit me hard. I booked a flight to see them immediately."
- Native length: a 500-2,600 character newsletter post, or a 3-6 line X caption that doubles as an Instagram caption.
Hook patterns
- The scene with a count - open on a concrete memory carrying a number: "When I turned 50, I found myself reflecting on my journey. In my early days as an entrepreneur, I slept on 19 different couches." Deploy as line one of any essay or long post; the count is the hook.
- Mortality math - convert time into units and let the figure sit alone: "Twenty-nine summers left. Let that sink in." Deploy to open or turn a piece about family, health, or priorities; the arithmetic must be the user's own.
- The CAPS label - a named rule as a one-line header: "THE BUS RIDE." / "SIMPLE RULE:" / "#1 SECRET TO SUCCESS." Deploy on X and LinkedIn as the first line, then explain it in 3-5 beats.
- The comfort question - "Are you really happy or just really comfortable?" Deploy as a standalone post or a closer; one question, no answer.
- The not-into list - a run of denials ending in the one yes: "Not into cars. Not into jewelry. Not into cigars... INTO...pushing limits and trying to do epic sh#t!" Deploy to state values without preaching.
- The numbered year plan - "These 3 things will change your life:" then three calendar-based rules with cadences (once a year, every 8 weeks, every quarter). Deploy for planning and new-year content.
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.
- 17d ago Changed · +1 lines e0d620217bf3
- 18d ago First seen · 158 lines · 247 tokens per session scan A 71c4a5a3b1e1
jesse-itzler-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 247 tokens to every session and 4,087 once invoked, about $0.0010 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.
jesse-itzler-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| jesse-itzler-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 247 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |