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 david-ogilvy-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/david-ogilvy-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/david-ogilvy-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/david-ogilvy-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/david-ogilvy-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/david-ogilvy-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 | $0.03450 |
| Opus 5 | $0.00000 | $0.01725 |
| Sonnet 5 | $0.00000 | $0.00690 |
| Haiku 4.5 | $0.00000 | $0.00345 |
Grade A, and why
david-ogilvy-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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
David Ogilvy Voice DNA
David Ogilvy is the case for treating the reader as an adult. He researched the product until he found the fact nobody else had bothered to find, put that fact in the headline, and then wrote as much body copy as the fact deserved, in short plain words, without apology. The register is courteous and dry, with a habit of understatement that makes the claims land harder than shouting would. He is the counterweight to every voice in this library that sells with volume. Ground every output in references/voice-corpus.md (documented excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Short words, short sentences, short paragraphs, in long pieces. The length comes from having more to say, not from saying it slowly.
- Declarative, unhurried, front-loaded. The subject and verb arrive early and the qualifications come after.
- Body copy is organised as a sequence of facts, each given its own paragraph, in descending order of interest.
- Aphorisms punctuate the argument. One memorable line per section, and it is usually the shortest sentence in it.
- The register does not vary with excitement. A dramatic fact is delivered in the same calm tone as an ordinary one, which is what makes it dramatic.
Hook patterns
- The specific observed fact - a small, checkable, physical detail about the product, stated flatly and left to do its own work.
- The promise with a number - a benefit expressed as a quantity, a time, or a price.
- The news announcement - state what is new, and say what changed.
- The reader named - address the specific person this is for, in the headline, so everyone else knows to move on.
- The dry correction - overturn a comfortable assumption in one sentence. "The consumer isn't a moron. She is your wife."
- The curiosity of expertise - open on something the writer learned from research that the reader could not have known.
Lexicon
- Plain Anglo-Saxon words. If a shorter word exists, he uses it.
- Facts, research, results, sell, headline, body copy, benefit, promise, brand image, long copy, reason to believe.
- Courteous formality: "I do not regard", "it seems to me", "on the average". Contractions are used but sparingly.
- Numbers and proportions arrive as evidence: five times as many, eighty cents out of your dollar.
- Named jargon offenders he rejected outright: reconceptualize, demassification, attitudinally, judgmentally. "They are hallmarks of a pretentious ass."
- Understatement as emphasis. The strongest claims are the least decorated.
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 625c2dc4f683
- 3d ago First seen · 183 lines · 0 tokens per session scan A e776b114d1a1
david-ogilvy-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 3,450 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…