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 claude-hopkins-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/claude-hopkins-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/claude-hopkins-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/claude-hopkins-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/claude-hopkins-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/claude-hopkins-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 | $0.00240 | $0.04247 |
| Opus 5.5 | $0.00096 | $0.01699 |
| Sonnet 5.5 | $0.00048 | $0.00849 |
| Haiku 4.5 | $0.00024 | $0.00425 |
Grade A, and why
claude-hopkins-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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Hopkins Voice DNA
Claude Hopkins is the man who made advertising answer to a coupon count. He wrote in short flat sentences because the common people he sold to feared literary style, he anchored every rule to a traced return because mail order had taught him that guesswork was a confession, and he judged every line by whether a salesman would say it to one buyer face to face. The register is doctrinal and plain: parallel negations ("It is not for general effect. It is not to keep your name before the people."), parallel imperatives ("Don't try to be amusing. Don't boast."), a homely simile, and a one-line moral to close. The memoir adds first person and a reported scene but keeps the cadence. Both books are public domain, so the excerpts here are his exact words. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Short indicative sentences of 4-9 words stacked three to six deep with no connective: "Advertising is salesmanship. Its principles are the principles of salesmanship. Successes and failures in both lines are due to like causes."
- Parallel negation and parallel imperative are the two building blocks: "It is not for general effect. It is not to keep your name before the people." / "Don't try to be amusing. Money spending is a serious matter. Don't boast, for all people resent it."
- The only hinges are "Thus", "So", "Therefore", "That being so". Subordinate clauses are rare and short.
- Paragraphs run 3-6 sentences and end on the principle. Chapters run 800-1,500 words and close on a one-line moral.
- A number arrives within a sentence or two of every claim: "Again and again we see 20 percent of all the readers of a newspaper cut out a certain coupon."
- The memoir register adds first person and reported dialogue at the same tempo: "I came back to the office amazed. I said: "Why don't you tell people these things?""
Hook patterns
- The flat law - state the principle as a settled fact in four words: "Advertising is salesmanship." / "Human nature is perpetual." Deploy as the first sentence of any doctrinal piece; the rest of the paragraph is its consequence.
- The denied commonplace - name the common belief and dismiss it in one short sentence: "It is commonly said that people do not read advertisements. That is silly, of course." Deploy to open a correction, then pay it with a traced figure.
- Hey there, Bill Jones - the headline as a shout to one person in a crowd: "The purpose of a headline is to pick out people you can interest." Deploy as the headline test on every piece: does it name the buyer?
- The cost comparison - put the wasteful figure beside the possible one: "Men spending five dollars to do what one dollar might do. Men getting back 30 percent of their cost when they might get 150 percent." Deploy to make waste concrete.
- The untold common story - the fact every competitor has and none has stated: "I told a story common to all good brewers, but a story which had never been told. I gave purity a meaning." Deploy as the research brief for reason-why copy.
- The costly habit - a vivid instance of a project that fails on arithmetic: "To sell shaving soap to the peasants of Russia one would first need to change their beard-wearing habits. The cost would be excessive." Deploy to kill a brief before money is spent.
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 · 174 lines · 240 tokens per session scan A 08d6c5b36d0d
claude-hopkins-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 240 tokens to every session and 4,247 once invoked, about $0.0010 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.
claude-hopkins-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-hopkins-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 240 | 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 |