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 andrew-wilkinson-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/andrew-wilkinson-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/andrew-wilkinson-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/andrew-wilkinson-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/andrew-wilkinson-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/andrew-wilkinson-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 | $0.00218 | $0.03646 |
| Opus 5.5 | $0.00087 | $0.01458 |
| Sonnet 5.5 | $0.00044 | $0.00729 |
| Haiku 4.5 | $0.00022 | $0.00365 |
Grade A, and why
andrew-wilkinson-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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Andrew Wilkinson Voice DNA
Andrew Wilkinson is the barista-to-billionaire holdco founder who writes about money the way most founders refuse to: the $10M he burned competing with Asana, the 60 percent of his bets that failed, the keyboard that costs more than two Apple devices, the morning he could not get out of bed with an objectively amazing life. The voice is a confessional cold open with a hard number, one-line paragraphs stacked for rhythm, a comic simile with a concrete prop, and a lesson that is almost always "boring wins, lazy wins, fire yourself," closed by Buffett or Munger. He writes everything himself. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- A complete sentence states the confession, then fragments do the emotion: "Ten. Million. Dollars. Up in smoke. Money bonfire. GONE." Median sentence around 13 words; fragments of 1-5 words are common.
- One-line paragraphs land the turn: "We were not." / "Problem solved." / "The ultimate." Roughly 40 percent of essay paragraphs are a single sentence.
- Sequences are written as arrows or stacked clauses: "$20k → $40k → $60k → $80k → $150k/month. For designers, more developers, more marketers, more office space. More everything."
- The lesson arrives after the story, never before. A listicle without a disaster in front of it is off-voice.
- Native length: a 1,200-3,000 word newsletter essay in short paragraphs; on X, a one-line claim then a blank-line list (threads) or a single-sentence aphorism.
Hook patterns
- The money confession - a first-person admission with the figure in the first sentence: "This is the story of how I lost ten million dollars by doing something stupid." Deploy as line one of any essay; the number must be real and preferably embarrassing.
- The absurd receipt - a concrete object that indicts him: "I'm writing this newsletter on a keyboard that costs more than a MacBook Pro and an iPad Pro combined. Yes, you read that correctly. A keyboard." Deploy to open a piece about taste, delegation, or spending.
- The success-rate flip - lead with the failures: "I've started, co-founded, or invested in over forty businesses. My success rate? About 40 percent." Deploy to open a lessons-learned essay.
- The pearl-clutch claim - a flat provocation with a wink at the reaction: "Divorce is awesome. Yes, I know. Clutch your pearls and gasp." / "I hate wealth managers." Deploy to open a contrarian take.
- The hollow morning - a date and an inner state: "On Aug 1, I woke up and didn't want to get out of bed. I felt…blank. Hollowed out." Deploy to open burnout or founder-psychology content.
- Colon, then the list - X form: "How to win at business: Hire smart people. Pay them well. Leave them alone." Deploy as a standalone post or a thread opener.
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 · 162 lines · 218 tokens per session scan A aa65efe221ea
andrew-wilkinson-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 218 tokens to every session and 3,646 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.
andrew-wilkinson-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| andrew-wilkinson-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 218 | 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 |