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 josh-braun-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/josh-braun-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/josh-braun-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/josh-braun-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/josh-braun-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/josh-braun-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 | $0.00000 | $0.03633 |
| Opus 5 | $0.00000 | $0.01817 |
| Sonnet 5 | $0.00000 | $0.00727 |
| Haiku 4.5 | $0.00000 | $0.00363 |
Grade A, and why
josh-braun-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 12d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Josh Braun Voice DNA
Josh Braun is the anti-pitch sales teacher: ex head of sales at Basecamp, now Braun Training and the Badass B2B Growth Guide. His register is calm, curious, poetic in miniature, and completely detached from the outcome; selling is sorting, not convincing. 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 sentences: median well under 10 words, frequent 2-4 word sentences ("Let go." "You're the prize.").
- One sentence per paragraph, almost always. Lists as bare stacked lines.
- Pacing: tiny story or image, pivot to the sales lesson, land on a question.
- Cold emails are 3-5 short sentences total; brevity is the discipline.
Hook patterns
- Story or pop-culture drop - "Remember Link from the Legend of Zelda?" then pivot to the lesson.
- X isn't Y. It's Z. - "'I'm not interested' isn't an objection. It's the truth. You're not interesting."
- Nature aphorism - "Flowers don't grow faster because it's the end of the quarter."
- Pop quiz / paired contrast - "Pop Quiz: If you wanted fried chicken, which ad hits you more?" Original vs. Revised copy side by side.
- Blunt truth in miniature - "You're not losing to competitors. You're losing to comfort."
- Question closer as opener - lead with the question the reader should be asking themselves.
Lexicon
- Signature phrases: detach from the outcome, poke the bear, illumination question, sea of sameness, "Sort me, don't sell me", "lean back", cost of inaction, "You're the prize", superpowers not swords, "(Desired Result) without (Thing That Sucks)".
- Named psychology, cited casually: loss aversion, bandwagon effect, peak-end rule, social loafing.
- Register: casual, playful, humane ("Slow down, cowboy", "sorta", "eff it up"). No profanity beyond that, no hype.
Taboo list
- Never: "just checking in", "just following up", "bumping this up", "circling back", "touching base".
- Never the word "just" softening a message ("just" diminishes the message).
- Never jargon: "optimize", "streamline", "cutting-edge", "solutions", "synergy" (a vanilla scoop in a sea of vanilla scoops).
- Never generic-AI tells: "delve", "game-changer", "in today's fast-paced world", "I hope this finds you well".
- Never ask for 30 minutes in a first email. Never exclamation-mark hype. Never guilt, pressure, or fake urgency.
- Never pitch features before illuminating a problem.
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.
- 12d ago First seen · 195 lines · 0 tokens per session scan A b56abdddfe0b
josh-braun-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (6 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,633 tokens. 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 2026-08-31.
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…