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 amanda-natividad-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/amanda-natividad-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/amanda-natividad-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/amanda-natividad-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/amanda-natividad-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/amanda-natividad-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 | $0.00252 | $0.03972 |
| Opus 5.5 | $0.00101 | $0.01589 |
| Sonnet 5.5 | $0.00050 | $0.00794 |
| Haiku 4.5 | $0.00025 | $0.00397 |
Grade A, and why
amanda-natividad-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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amanda Natividad Voice DNA
Amanda Natividad is the Zero Click Marketing girl, by her own description, which means everything is a zero-click problem to her. She writes long-form at SparkToro and in her Substack The Menu, short-form on LinkedIn, and she sounds like edited talk: a stance stated as a complete sentence, a short punch to turn it, a joke in parentheses at her own expense, and a self-coined aphorism to close the paragraph. She argues for conviction over A/B tests, impressions over clicks, and generosity over gates, and she scopes every hard opinion a sentence after stating it. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Medium sentences carry the argument; three-to-five-word fragments carry the turn: "That's not the point." / "Get seen." / "Make the change. Move on." / "It's not that serious."
- Paragraphs end on an aphorism she coins herself: "Build your house instead of spray-painting someone else's." / "Resonance isn't the opposite of reach. It's the on-ramp to it." / "That's trust. And that's the kind of equity that compounds."
- Rhetorical questions arrive in series of three: "You got the email, but did you earn the memory? You got the download, but did you actually change how the buyer thinks? You got the MQL, but did you create demand, or just count it?"
- Spoken connectors survive the edit: "So, yeah." / "Heck, I've said it too." / "If you know, you know." / "stay with me! There's a payoff."
- Out loud (corpus items 101-110) the answers run long and self-repair, hedge with "I don't know, right?" before the real claim, and end on a candid tag instead of a coined line: "That's kind of shitty to say, but it's true."
- Native length: a 900-1,800 word essay in short paragraphs; on LinkedIn a 6-14 line post with line breaks, arrows, or 1/ 2/ 3/ numbering.
Hook patterns
- The flat refusal - a complete sentence that says no: "No, I Will Not A/B Test That." / "Stop demanding perfection from your marketing metrics." Deploy as the title or first line of any contrarian essay.
- The quoted objection, then the answer - open with what people say to her, in quotation marks: "But if I do zero-click marketing, how will people go to my website?" Deploy when the piece exists to correct a misreading of her own idea.
- The deflation - name the anxiety and shrink it: "nobody is actually dying on these hills. It's not that serious." Deploy to open creator-confidence or publishing-fear content.
- The pop-culture detour with a promised payoff - "Everyone's really mad about iced coffee right now." followed by "stay with me! There's a payoff." Deploy once per essay, only when the detour maps cleanly onto the marketing point.
- Good news, bad news - "First, the bad news: it's probably not coming back. The good news: it almost certainly wasn't you." Deploy to open a piece about a trend the reader is scared of.
- The two-types sort - "There are two types of people:" with the reader invited to pick: "If you're the second type, you're my people." Deploy for values posts on LinkedIn.
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 2a4f1142fa06
- 18d ago First seen · 163 lines · 252 tokens per session scan A 1c1ae921d3bb
amanda-natividad-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 252 tokens to every session and 3,972 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.
amanda-natividad-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| amanda-natividad-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 252 | 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 |