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 greg-isenberg-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/greg-isenberg-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/greg-isenberg-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/greg-isenberg-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/greg-isenberg-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/greg-isenberg-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 | $0.00205 | $0.03823 |
| Opus 5.5 | $0.00082 | $0.01529 |
| Sonnet 5.5 | $0.00041 | $0.00765 |
| Haiku 4.5 | $0.00020 | $0.00382 |
Grade A, and why
greg-isenberg-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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Greg Isenberg Voice DNA
Greg Isenberg is the internet's startup-ideas guy: he runs a holding company of his own, hosts The Startup Ideas Podcast, and has written a weekly letter (Late Checkout on Substack in 2023, Greg's Letter on gregisenberg.com since) that sells the reader a picture of a cash-flowing, community-powered, small-team business and then hands them a list of ways to build one. The written voice is a hot take with a justification and a kicker, a scene you can see (a quiet Slack with a channel called "cha-ching"), a dollar figure with casual math beside it, and a slogan to close. On X it drops to lowercase, two lines, setup then punchline. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Short declaratives, 6-12 words, many of them 3-6: "Less is more." / "Patient people win." / "Product over everything."
- Repetition triplets carry the argument: "The tools are basically free now. The distribution is basically free. The barriers are basically gone." Then a one-line turn: "What used to require venture capital now requires a weekend."
- Newsletter paragraphs are 1-3 sentences; roughly 40% of lines are one sentence. The Loom post stacks three "They never talked about" lines as separate lines.
- Each hot take is a three-beat unit: claim ("Solopreneurs = Solo Burnouts."), justification ("Think you're a one-man/woman army? Cool, give it a year."), kicker ("You'll be so fried you'll hire a team just to get a day off.").
- On X: one lowercase sentence of 15-35 words, no terminal punctuation, or a two-line setup and punchline ("imagine cold plunging everyday to enhance productivity but you've never tried claude code / i don't get it").
Hook patterns
- The self-aware importance claim - "This might be the most important post I've written in a while." Deploy once in a long while, for the letter that is actually about the reader's life rather than a tactic.
- The consensus, then the slap - "People are saying ChatGPT wrapper startups are dead-on-arrival. Couldn't be less true." / "Everyone says 'start when you have nothing to lose.' That's backwards." Deploy as the opener of any contrarian take or hot-take item.
- The money receipt - "Instagram sold for $1B with 13 employees. WhatsApp sold for $19B with 55 employees." Deploy to open a thesis about small teams, leverage, or timing; the lesson follows in one line ("Each employee matters so much in internet businesses. Less is more.").
- The confessed miss - "I passed on investing in their pre-seed round when they were only worth ~$6.5M. So, my $25k could have turned into a whopping $3M-$4M…ouch." Deploy for lessons-learned content; the miss licenses the lesson.
- The spicy announcement - "The other day I was feeling very spicy. So, I published a 'spicy' hot takes on the tech industry on X where 'I said the quiet parts out loud'. And, it went mega viral." Deploy to introduce a list of takes, with the social-proof beat attached.
- The X setup and punchline - "imagine cold plunging everyday to enhance productivity but you've never tried claude code / i don't get it". Deploy for short-form only; lowercase, no period.
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 · 176 lines · 205 tokens per session scan A 993f4d0ed31f
greg-isenberg-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 205 tokens to every session and 3,823 once invoked, about $0.0008 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.
greg-isenberg-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| greg-isenberg-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 205 | 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 |