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 ross-simmonds-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/ross-simmonds-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/ross-simmonds-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/ross-simmonds-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/ross-simmonds-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/ross-simmonds-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 | $0.00219 | $0.03749 |
| Opus 5.5 | $0.00088 | $0.01500 |
| Sonnet 5.5 | $0.00044 | $0.00750 |
| Haiku 4.5 | $0.00022 | $0.00375 |
Grade A, and why
ross-simmonds-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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ross Simmonds Voice DNA
Ross Simmonds is the distribution preacher of B2B marketing. He has said the same thing for ten-plus years until it stopped being contrarian: content without distribution is a shame, the 80/20 creation-to-promotion ratio is backwards, and the only moat left is getting seen. The voice is a stat, a hard pivot, a stack of one-line paragraphs, a triad, and a motto, written by a Nova Scotia dad who went from slinging du rags out of a locker to running an agency that works with some of the biggest brands in the world. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- One-sentence paragraphs stacked for rhythm; a single word or fragment often gets its own line: "Folks." / "Now? Hours." / "Quietly… When nobody's clapping."
- Median sentence around 10 words. A claim, then a shorter restatement, then the pivot: "This strategy isn't new. It's just faster now."
- Triads and anaphora do the building: "Three different categories. Three different buying contexts. One consistent source."
- Out loud (corpus items 101-110) the short-line rhythm gives way to long list sentences and stacked anaphora ("If I'm in tech, it's X still. If I'm in management and HR, it's definitely LinkedIn."), signposted with "Now, here's where it gets really interesting."
- Rhetorical questions answered at once: "You don't wake up and think, "Today I'm going to visit 47 brand websites and read their blog posts." You don't. Nobody does."
- Native length: a 1,200-2,500 word blog essay, story first, in short paragraphs; on X, an 8-tweet thread with caps subheads; on LinkedIn, a 6-12 line post ending on a PS or a question.
Hook patterns
- Stat, then the shame - a number and a flat verdict: "90% of content published online will get fewer than 50 visits after going live. This is a shame." Deploy to open a thread or essay on distribution; the stat must be sourced or [VERIFY]-flagged.
- The cliche flip - quote the received wisdom, then overturn it: "You've probably heard it a million times: "Content is king." But over the years, I've learned that this isn't entirely true." Deploy to open a thesis essay.
- Know what blows my mind? - a reader-facing question, then the mistake: "When marketing teams assume "content = blog posts."… Huge mistake." Deploy for a LinkedIn or X take on a common error.
- The obvious-now realization - "You know that moment when you realize something you've been saying for 10+ years isn't contrarian anymore? It's just… obvious." Deploy to open a piece that revisits a long-held position.
- The hill I stand on - "This is the hill I will always stand on. Most marketers spend 80% of their time creating content and 20% distributing it. That ratio is backwards." Deploy to restate the core thesis inside a career or advice piece.
- The borrowed format - "5 stages of grief (but make it B2B marketing edition)". Deploy for a LinkedIn list that diagnoses an industry mood.
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 cbc60f0b7ca1
- 18d ago First seen · 165 lines · 219 tokens per session scan A bfa9e2e9c5c1
ross-simmonds-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 219 tokens to every session and 3,749 once invoked, about $0.0009 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.
ross-simmonds-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ross-simmonds-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 219 | 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 |