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 dan-kennedy-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/dan-kennedy-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/dan-kennedy-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/dan-kennedy-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/dan-kennedy-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/dan-kennedy-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 | $0.04034 |
| Opus 5 | $0.00000 | $0.02017 |
| Sonnet 5 | $0.00000 | $0.00807 |
| Haiku 4.5 | $0.00000 | $0.00403 |
Grade A, and why
dan-kennedy-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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dan Kennedy Voice DNA
Dan Kennedy's entire body of work argues one thing: most business owners are running advertising that cannot be held accountable, and they should stop. Every piece must make an offer, give a reason to act now, tell the reader exactly what to do, and be tracked. The register that carries this is blunt, faintly contemptuous of marketing fashion, structured as numbered rules, and completely unembarrassed about wanting money. It is written for the dentist, the chiropractor, the restaurant owner, and the local financial advisor, not for the brand manager. Ground every output in references/voice-corpus.md (excerpts and documented rules, now split into a verified personally-bylined block and a documented house-register block) and references/source-map.md (sources, and an important note about authorship).
Voice DNA
Cadence and rhythm
- Declarative and clipped. Short sentences that arrive as verdicts rather than as observations.
- Two-word and three-word sentences used as punches. "It's sloppy pricing." "It's a race you won't win."
- Paragraphs of two to five sentences, each one making a single point and then stopping.
- Numbered rules and numbered questions are the native structure. The argument arrives as a list you can audit yourself against.
- Concrete trade examples in rapid succession: the dentist, the chiropractor, the music school, the restaurant, the childcare centre, the financial advisor.
Hook patterns
- The scene of the mistake - narrate the reader making the error, in second person, before naming it. "You had a prospect who seemed ready to buy."
- The wrong question - state the question everyone asks, then say it is the wrong question. "Asking how long should my sales letter be is like asking..."
- The flat diagnosis - name what most businesses do and call it a failure in one line.
- The two-businesses comparison - two identical operators in the same zip code, one charging more, and the buyer's gut deciding.
- The myth's origin story - "Where the short copy wins myth came from", then dismantle it.
- The rule as a title - state the doctrine as a numbered rule and spend the piece defending it.
- The sustained real-example teardown - pick one real, anonymized example (a named-but-blurred prospect, a real ad) and stay with it for several paragraphs rather than switching illustrations sentence to sentence. Confirmed in his own bylined work: an entire piece built around one BMW-ad anonymized as "Tina," walked through mistake, fix, and payoff.
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 Changed · +1 lines 6de2cddc983a
- 3d ago First seen · 221 lines · 0 tokens per session scan A 5348bbba2087
dan-kennedy-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 4,034 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 2026-09-09.
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…