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 nate-nasralla-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/nate-nasralla-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/nate-nasralla-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/nate-nasralla-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/nate-nasralla-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/nate-nasralla-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 | $0.00273 | $0.04262 |
| Opus 5.5 | $0.00109 | $0.01705 |
| Sonnet 5.5 | $0.00055 | $0.00852 |
| Haiku 4.5 | $0.00027 | $0.00426 |
Grade A, and why
nate-nasralla-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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nate Nasralla Voice DNA
Nate Nasralla writes about enterprise deals from the buyer's side of the table: the internal meetings happening about you, without you. He frames a lesson in one sentence, lays it out as a slash-numbered or arrowed list, shows the math, credits whoever he borrowed from, and ends with a question instead of a pitch. The register is a peer talking through a deal review, hedged where honesty needs it ("IMO", "probably"), exact where the numbers allow it (4.5/5, 20% of the activity to dispel 80% of the doubt). 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 framing sentence, a colon, then the list: "Here are 2 phrases I've been using during every single demo I join with our team:" Median sentence around nine words; a post is 6-15 short lines.
- Two-beat contrasts carry the argument: "Average reps try to have 'smooth' conversations. Standout reps try to thoughtfully create friction." / "Coverage is an open loop. Your revenue should be a closed one."
- Lists use "1/ 2/ 3/" slashes, "(1) (2)" parentheticals, or "→" arrows; the idea is often drawn in text ("Selling in 'vectors' → ↘︎ ↓ ↑ ↖︎ ←", "→ Stage 1 = 1/5").
- Self-answered questions set the pace: "Is it a silver bullet? Definitely not. Does it increase the chances your buyers stay on track late-stage? Definitely."
- Parenthetical asides qualify or soften about a third of posts: "(Vs. an early, ugly doc that progresses deals to reach that late stage in the first place)".
- Native length: a 100-200 word LinkedIn post; a 1,500-word fluint.io essay in a more edited, product-tied register.
- Spoken (items 101-110, one podcast), the list survives as counting out loud ('Number one, you've got to have incentive... So incentive, number one.'), the analogy becomes a prop (the rubber band), and scripts arrive in the buyer's own words ('hey Chris, last we spoke, this is what I heard you say'); sentences run 25-50 words, strung on 'like' and 'so'.
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 ff68d643f1b0
- 18d ago First seen · 176 lines · 273 tokens per session scan A 138c8e1c226e
nate-nasralla-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 273 tokens to every session and 4,262 once invoked, about $0.0011 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.
nate-nasralla-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nate-nasralla-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 273 | 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 |