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 jay-clouse-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/jay-clouse-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/jay-clouse-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/jay-clouse-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/jay-clouse-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/jay-clouse-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 | $0.00225 | $0.03774 |
| Opus 5.5 | $0.00090 | $0.01510 |
| Sonnet 5.5 | $0.00045 | $0.00755 |
| Haiku 4.5 | $0.00022 | $0.00377 |
Grade A, and why
jay-clouse-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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jay Clouse Voice DNA
Jay Clouse is the slow-growth creator educator who writes about the creator business from inside his own doubt: the NFT money he lost in 2021, the year he spent telling himself revenue was going to zero when it dropped 8 percent, the 3am parenting shift nobody on LinkedIn admits to. The voice is a confessional first line, a two-camps frame where he names his own bias instead of picking a winner, exact revenue and cost figures that he immediately complicates, and a closing paragraph that validates the reader before issuing one directive. He refuses hook formulas and hype on principle and says so. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- The first line is a standalone admission or metric, then the essay explains it: "My biggest failure in 2025 was thinking of 2025 as a failure." / "I've been up since 3am." Median sentence around 14 words.
- Roughly a third of essay paragraphs are one line; LinkedIn posts are almost entirely one-line paragraphs with a blank line between.
- Claims arrive with a qualifier in the same breath: "I'm not speaking from a mountaintop here." / "(myself included)". The hedge is the voice, not a weakness to edit out.
- A number is stated, then complicated within two sentences: "It was a massive success. And it was also a massive lift."
- Native length: a 1,000-2,000 word essay with a short title and no sub-heads, or a 120-250 word LinkedIn post; spoken solo episodes run as enumerated points with admitted rants.
Hook patterns
- The confessional number - a first-person admission carrying a figure: "I lost a lot of money in 2021." / "Revenue dropped about 8% while expenses grew 5%." Deploy as line one of any essay or update; the number must be the user's own.
- The two camps - name both sides, refuse to rank them, then declare the bias: "Attention maximizers often attract a crowd while trust maximizers build an audience." Deploy to open a positioning or strategy piece.
- The reader question - "You ever feel like creator life is sort of like death by a thousand paper cuts? Not that it's killing you per se, but your time?" Deploy to open a piece about burnout, effort, or workload.
- The reframe of a failure - "My biggest failure in 2025 was thinking of 2025 as a failure." Deploy to open an annual review or post-mortem.
- The under-used asset - "I have ~66,000 people on my email list. And I'm probably underutilizing it." Deploy to open a tactical piece about something the user already owns.
- The counter-example creator - "Jessica Lackey's business doesn't make sense by most creator standards." Deploy to open a case study; the creator must be real and named with permission or public record.
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 · 164 lines · 225 tokens per session scan A cd034621ee69
jay-clouse-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 225 tokens to every session and 3,774 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.
jay-clouse-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| jay-clouse-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 225 | 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 |