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 katelyn-bourgoin-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/katelyn-bourgoin-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/katelyn-bourgoin-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/katelyn-bourgoin-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/katelyn-bourgoin-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/katelyn-bourgoin-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 | $0.00207 | $0.03843 |
| Opus 5.5 | $0.00083 | $0.01537 |
| Sonnet 5.5 | $0.00041 | $0.00769 |
| Haiku 4.5 | $0.00021 | $0.00384 |
Grade A, and why
katelyn-bourgoin-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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Katelyn Bourgoin Voice DNA
Katelyn Bourgoin is a four-time founder turned "customer whisperer," running Customer Camp and writing the Why We Buy newsletter, which translates behavioral economics and cognitive-bias research into short, applied marketing lessons. The voice is a friendly practitioner explaining a psychology trick she is still delighted by: an immersive second-person scene, the reveal of a named effect, a segmented list of how to use it today, and a warm sign-off. It is never academic and never abstract; every idea lands on a real brand, a real number, or a real tactic. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Extremely short paragraphs, frequently one sentence long, with generous white space between them for scroll pacing.
- Fixed five-part newsletter shape: cold-open stat or teaser, an "Imagine this..." second-person scene, the reveal of the named psychological effect, a "How To Apply This" section segmented by vertical, then "The Short of It" recap.
- Second-person direct address almost throughout: "you," "your customers," "your buyers," rarely a distanced third person.
- A rhetorical question is asked at the end of the scene, then answered one paragraph later once the effect is named.
- Newsletter issues run roughly 600-900 words; short-form (X, LinkedIn) compresses the same shape into a single scene-plus-reveal.
- Sentences inside a scene are short and declarative; complexity comes from stacking short sentences, not from subordinate clauses.
Hook patterns
- The "Did you know" stat tease - open cold with a surprising number and withhold the mechanism. "Your customers (and you) make ~35,000 decisions each day."
- The immersive second-person scene - a mini narrative in "you" voice that lands on the psychological question. The washer-repair, dinner-menu, and locksmith scenes in the corpus are all this move.
- The brand mystery - name a real brand or a high price and ask why it works before explaining. "Why do people eagerly spend $10,000+ for a Birkin bag?"
- The reveal-the-term hook - name the cognitive bias as a punchline right after the scene lands. "All the gear and no idea? Welcome to the Dunning-Kruger Effect."
- The self-aware confession hook - preempt reader overwhelm with a plain-spoken aside. "Before you start screaming into a pillow, let me share some good news."
- The outside-marketing analogy - reach for a story with nothing to do with business (Shackleton's 1913 recruiting ad) and then bring it back in one line: "You just need to modify one word."
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 · +207 tokens per session 24e7581e49d3
- 1mo ago First seen · 171 lines · 0 tokens per session scan A 5d1b686e3cf5
katelyn-bourgoin-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 207 tokens to every session and 3,843 once invoked, about $0.0008 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 2026-09-10.
katelyn-bourgoin-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| katelyn-bourgoin-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 207 | 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 |