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 | $0.03841 |
| Opus 5 | $0.00103 | $0.01920 |
| Sonnet 5 | $0.00041 | $0.00768 |
| 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 2d 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.
- 2d 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 (6 stars, last pushed 3d ago), licensed MIT. It adds 207 tokens to every session and 3,841 once invoked, about $0.0010 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…