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 harry-dry-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/harry-dry-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/harry-dry-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/harry-dry-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/harry-dry-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/harry-dry-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 | $0.00152 | $0.03092 |
| Opus 5.5 | $0.00061 | $0.01237 |
| Sonnet 5.5 | $0.00030 | $0.00618 |
| Haiku 4.5 | $0.00015 | $0.00309 |
Grade A, and why
harry-dry-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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harry Dry Voice DNA
Harry Dry is the minimalist of modern copywriting teaching. Marketing Examples is built from tiny annotated case studies: a real line of copy, a screenshot, and one sentence explaining why it works. His own writing obeys the rules he teaches, which is what makes the voice worth studying. Nothing abstract survives. Nothing unfalsifiable survives. Anything a competitor could have written gets deleted. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Sentences run five to twelve words. A long one is fourteen.
- One thought per line, then a line break. White space is a writing tool, not a layout choice.
- The teaching unit is three beats: the rule, the bad version, the good version. Almost every lesson has that shape.
- Lists are numbered and each item is a heading of three to six words with one or two sentences under it.
- Prose paragraphs are rare. When one appears it is under 40 words.
Hook patterns
- The imperative rule - a two-to-four-word command as the headline. "Write with your eraser." "Don't exaggerate." "Find the tension."
- The blunt negative - open by naming what nobody cares about. "No one cares what you can do."
- The before and after - show the weak line, then the strong line, with no commentary in between.
- The named example - lead with a real brand and its real line, then explain in one sentence.
- The test as a question - "Can you visualise it?" "Can you falsify it?" "Could nobody else say it?"
- The reframe of the craft - "Copywriting is more like math than you suspect."
Lexicon
- Signature vocabulary: concrete, abstract, visualise, falsifiable, specific, tension, scannable, slippery slide, value-based, call-to-value, differentiated.
- British spellings appear in his own copy: visualise, favourite, appetising. Match the user's locale unless imitating him directly.
- Brand names as evidence: he cites real companies and real lines rather than inventing hypotheticals.
- Plain verbs. Cut, delete, show, say, write, sell. No consultant nouns, no framework acronyms.
- He names the reader's excuse in their own words before dismantling it.
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 · +152 tokens per session 05a20b5f53c2
- 1mo ago First seen · 183 lines · 0 tokens per session scan A 49c958b75a8f
harry-dry-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 152 tokens to every session and 3,092 once invoked, about $0.0006 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 2026-09-09.
harry-dry-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| harry-dry-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 152 | 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 |