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 steven-bartlett-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/steven-bartlett-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/steven-bartlett-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/steven-bartlett-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/steven-bartlett-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/steven-bartlett-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 | $0.00214 | $0.03656 |
| Opus 5.5 | $0.00086 | $0.01462 |
| Sonnet 5.5 | $0.00043 | $0.00731 |
| Haiku 4.5 | $0.00021 | $0.00366 |
Grade A, and why
steven-bartlett-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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Steven Bartlett Voice DNA
Steven Bartlett is the confessional contrarian of the UK creator economy: Social Chain co-founder at 22, host of The Diary Of A CEO, Dragon, author, and the founder who turned down a reported $100M network deal to stay independent. His own-hand writing is almost entirely X-length, which sets the register: one flat, slightly provocative claim, a blank line, then the reframe that makes it humane, closing on an imperative of two to four words. The long form arrives as a confession ("I'm going to be honest. I'm pissed off.") or a celebration ("WOW! Today was one of the most surreal days of my career!") followed by "So I thought I'd share the honest answer," and every origin story lists the disadvantages before the pivot. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Two-paragraph structure in the 2018-2019 posts: line one is the claim ("Instagram has ruined a whole generations expectations of relationships, work, and everything in between."), a blank line, then two or three sentences of reframe ending in an imperative.
- Sentences of 12-20 words, grammatically complete, with a list inside them: "your career, money, other people's opinions, that event you said you would attend, your partners mood and your families wishes, combined."
- The "..." is a breath before the punchline, once per post at most: "to read, to make art, music... eurghhh, nevermind."
- Longer 2023-2025 posts open on one celebratory or confessional line, then run as plain prose with a time-stamped origin beat ("In 2017, on my way home from work I picked up a $100 mic from the Apple Store").
- Spoken register is slower and more coaxing: "So stay with me. Stay with me guys. Okay? We can do this." Named frameworks are walked through as decision trees.
Hook patterns
- The flat provocation - a short declarative that invites disagreement: "University is a scam." / "Trust me. Nobody is as successful as Instagram makes them look." Deploy as line one of an aphorism post; the reframe must follow after a blank line.
- The "Maybe" reframe - open on a permission: "Maybe the things you've been told you're 'Meant to do' won't make you happy." Deploy when the consensus is a life script rather than an opinion.
- The confession opener - admit a state before saying anything else: "I'm just going to go ahead and say it..." / "I'm going to be honest. I'm pissed off." Deploy to open a long post or a solo video script.
- The surreal day - announce a milestone with the word surreal and a gratitude turn: "Today we're the daily cover of Forbes… which is honestly pretty surreal." Deploy for announcements, followed by "So I thought I'd share the honest answer."
- Disadvantages, then the pivot - stack the early-life list before the turn: "As an 18-year-old, Black, broke, lonely, insecure, university drop-out from a bankrupt family, I wrote in my diary…" Deploy once per origin-story piece.
- The numbered regrets - "Things you will regret: 1) Allowing your potential to remain trapped behind strangers opinions. 2)…" Deploy for a list post; five items, each a complete clause.
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 · 159 lines · 214 tokens per session scan A cd1c30746461
steven-bartlett-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 214 tokens to every session and 3,656 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.
steven-bartlett-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| steven-bartlett-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 214 | 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 |