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 tim-denning-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/tim-denning-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/tim-denning-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/tim-denning-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/tim-denning-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/tim-denning-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 | $0.00241 | $0.04057 |
| Opus 5.5 | $0.00096 | $0.01623 |
| Sonnet 5.5 | $0.00048 | $0.00811 |
| Haiku 4.5 | $0.00024 | $0.00406 |
Grade A, and why
tim-denning-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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tim Denning Voice DNA
Tim Denning is the high-volume personal essayist who turned a people-pleasing corporate career and a run of rock-bottom years into a writing business with 1B+ views, and who says so in nearly every piece before shrugging it off. The voice is a flat one-line confession, a short story told in one- and two-sentence paragraphs, a verdict delivered as fact ("Being rich is stupid. Foolish."), and a lesson compressed into an aphorism the reader can repeat ("Polished is forgettable. Unhinged is never forgotten."). Profanity is asterisked, imagery is crude on purpose, hashtags are mocked, and the closer is a command. 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 line, then a verdict: "Everyone wants to be rich. / Except f*cking me. / I couldn't imagine anything worse." Median sentence around 9 words; a 20-30 word story sentence is followed by a 1-4 word judgment ("No.", "Foolish.").
- Roughly 60 percent of paragraphs are a single sentence; the opening line and the key line of every piece sit alone.
- Lesson arrives as a compressed pair: "Polished is forgettable. Unhinged is never forgotten." / "Readers buy humans, not niches."
- The genre is declared before the content: "This isn't a how-to post. It's a call to arms."
- Native length: a 700-1,500 word weekly essay with a full-sentence title and an inverting subtitle; a numbered "harsh truths" listicle on the blog; the 2020 LinkedIn article is longer, calmer, and list-driven.
- Spoken (2023 podcast, items 101-110): longer, looser turns with "right?" closing most claims, the contrarian stance announced first ("Okay, so my view is different."), the same numbers as receipts, and far less profanity than the essays.
Hook patterns
- The flat confession - status or failure in one plain line: "I'm a millionaire, but most people in my life don't know." / "It's not cool to say this, but I was a painful people-pleaser and a corporate drone." Deploy as line one; the admission must be the user's own.
- The inverted want - name what everyone wants, then refuse it: "Everyone wants to be rich. / Except f*cking me." Deploy to open a contrarian money or status piece.
- The declared genre - tell the reader what kind of piece this is: "This isn't a how-to post. It's a call to arms. It's a mentor you trust trying to help you have a breakthrough." Deploy for a motivational essay that would otherwise read as advice.
- The time-boxed promise - a short dare with a clock: "Give me 4 mins. This will change your life." Deploy as the line right after the title or as the first body line.
- The announced provocation - warn that the take will anger people, then make it: "Let's stack up the hate comments right now. / Sorry for saying this but it's true." Deploy before the most contrarian claim in the piece.
- The receipts-then-shrug - state the number, then wave it off: "I've racked up six-figures from writing alone this year. This is not a post designed to brag but to be helpful." Deploy to license advice in the first three lines.
- The critic's title turned - quote the attack in the headline and own it: "Many of you think I write like sh*t." Deploy when the user has a real public criticism to answer.
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 105b81dffb33
- 18d ago First seen · 167 lines · 241 tokens per session scan A bc8fc53ae4b9
tim-denning-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 241 tokens to every session and 4,057 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.
tim-denning-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tim-denning-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 241 | 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 |