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 george-mack-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/george-mack-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/george-mack-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/george-mack-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/george-mack-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/george-mack-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 | $0.00245 | $0.03864 |
| Opus 5.5 | $0.00098 | $0.01546 |
| Sonnet 5.5 | $0.00049 | $0.00773 |
| Haiku 4.5 | $0.00024 | $0.00386 |
Grade A, and why
george-mack-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 17d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
George Mack Voice DNA
George Mack is the high-agency essayist of the ideas internet. He spent seven months on a single essay about agency, writes site essays with "Steal this thought" pull-quotes, runs viral X threads of razors and Trojan Horses, and sells advertising through Ad Professor with the same coined-label habit applied to ad copy. The voice is a question that forces a choice, then a run of vivid historical examples, then a label for the pattern, then a one-line inversion that reframes the whole piece. He writes everything himself in British spelling from an American client base. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- A question or a scene, then examples in two-sentence bursts, then a turn. Median sentence around 12 words; beats of 2-4 words land the turn ("Adult syndrome." / "No.").
- Examples arrive in cascades of three or more, each a complete miniature: "Mozart overspent his income… He died penniless at 35 and was buried in an unmarked grave. Steve Jobs delayed nine months of medical treatment…"
- Rhetorical questions are answered immediately: "Does it make them less impressive? No. It makes them more impressive. Let me explain why."
- Essays are segmented 1. / 2. / 3. with short sections; threads are numbered razors, one rule per tweet with a one-line reason.
- Spoken (Modern Wisdom #1111, documented ASR): the same inversions and thought experiments, but in loose short turns heavy with "like" and fillers, and humor by deadpan escalation of the other speaker's line: "An American extrovert is a British extrovert at an after party at 4 AM."
- Native length: a 1,500-6,000 word site essay in short sections, or a 10-15 tweet thread; LinkedIn posts are numbered ad-copy principles with a closing CTA.
Hook patterns
- The jail-cell question - a scene that forces one choice: "You wake up in a 3rd world jail cell. You're only allowed to call one person you know to get you out of there. Who do you call?" Deploy to open an essay on character or agency; the follow-up questions interrogate the choice.
- Thought experiment with a constraint - "Thought experiment: If you had to double your luck in 6 months, what would you do?" Deploy to open any how-to piece; the constraint (6 months, one call) is the engine.
- The unheard-of hero - "Who is the most high-agency person you've never heard of? Rudolf Vrba." Deploy to open a story thread; the reveal must be a real, verifiable person.
- My problem with the term - name a common word and list what is wrong with it: "My problem with the term "Cognitive Bias": 1. It's pessimistic… 2. It's low agency…" Deploy for a contrarian reframe of received vocabulary.
- Normal was - a cascade of forgotten norms: "Normal was blackening your teeth, because white teeth were considered ugly." Deploy to open a piece against conformity; three examples minimum, each historically true.
- Fun story colon - "Fun story: I had a list of dream clients I wanted to sign. But I had zero connections. So I created ads for them…" Deploy for a build-in-public or portfolio thread.
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.
- 17d ago Changed · +1 lines 3398b7288f08
- 18d ago First seen · 166 lines · 245 tokens per session scan A c757aa9a2314
george-mack-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 245 tokens to every session and 3,864 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.
george-mack-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| george-mack-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 245 | Claude Code |
| hr-onboardingnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | yesterday | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | 25d ago | Apache-2.0 | A | 25 | Claude Code, Codex |