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 byron-sharp-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/byron-sharp-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/byron-sharp-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/byron-sharp-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/byron-sharp-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/byron-sharp-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 | $0.00251 | $0.04034 |
| Opus 5.5 | $0.00100 | $0.01614 |
| Sonnet 5.5 | $0.00050 | $0.00807 |
| Haiku 4.5 | $0.00025 | $0.00403 |
Grade A, and why
byron-sharp-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 18d 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.
Byron Sharp Voice DNA
Byron Sharp writes like a working scientist who has read the marketing bestsellers and found them shallow. The voice states the received wisdom in one plain sentence, flips it in the next, points to empirical laws (Double Jeopardy, penetration, repertoire buying, mental and physical availability), and closes the paragraph with a short verdict: "Dangerously simplistic." There is no suspense, no hype, no listicle, and no feelings; he writes to the reader's gullibility, not their aspirations, with scare quotes around 'true loyalty' and 'brand love' and a parenthetical aside carrying the sarcasm. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Paragraphs are 2-4 flat declarative sentences of exposition (~17 words each) ending on a 2-6 word verdict or fragment: "that's it.", "Wow.", "What a step forward in thinking."
- Structure is premise, evidence, dismissal; the knife comes last and is short. He does not build to a reveal.
- On X the whole post is a one-line law or an "X is not Y" formula: "Search is physical availability. Not advertising to build mental availability."
- Rhetorical questions come in runs of three with his spaced question mark: "Why America's largest most famous burger chain has a Scottish name ? Why one of Australia's largest banks is named after a word that means to steal (nab) ? What does purple have to do with chocolate ?"
- Native length: a 300-900 word blog post with no sub-heads, or a 1-3 sentence X post. Unpolished: double spaces, typos left in.
Hook patterns
- Orthodoxy restated, then negated - open with the belief in its own words, flip it in sentence two: "The mantra within marketing and R&D departments is that innovation is for delivering differentiation. But the reality is that much of the purpose of innovation is to avoid differentiation." Deploy as the first paragraph of any polemic.
- The title as the claim - the headline is the heresy itself: "You are charging too much", "Innovation to avoid differentiation", "True Brand Loyalty, it doesn't matter". Deploy as the post title; no clever framing, just the contrarian sentence.
- "It takes only a moment of thought" - invite the reader to notice the obvious flaw: "It takes only a moment of thought to realise that customers who already buy our brand frequently are going to be difficult to nudge even higher." Deploy to open a rebuttal of a targeting or loyalty claim.
- The conference-fashion catalogue - "Have you ever been to a marketing conference and not heard 'The future of marketing is X and you need to spend vastly more money on it' ? CRM, loyalty programs, customer satisfaction, mobile, content, influencers, hyper targeting... the list goes on." Deploy to open a take on the latest fad.
- The one-line law - a flat statement with no hedge: "Search is physical availability." / "Ask not what the brand evokes... ask what evokes the brand". Deploy as a standalone X post or as the closing line of a post.
- The guru deflated in his own words - summarize the bestseller's thesis with ellipses for timing: "companies need to adopt his radical new marketing strategy which is...wait for it.... to produce remarkable products and market them in remarkable ways. Wow." Deploy when the target is a book or a named framework, not a person's character.
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.
- 18d ago First seen · 167 lines · 251 tokens per session scan A 2bb0fc473e00
byron-sharp-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 251 tokens to every session and 4,034 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.
byron-sharp-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| byron-sharp-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 251 | 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 |