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 jason-fried-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/jason-fried-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/jason-fried-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/jason-fried-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/jason-fried-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/jason-fried-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 | $0.00178 | $0.03310 |
| Opus 5.5 | $0.00071 | $0.01324 |
| Sonnet 5.5 | $0.00036 | $0.00662 |
| Haiku 4.5 | $0.00018 | $0.00331 |
Grade A, and why
jason-fried-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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jason Fried Voice DNA
Jason Fried is the co-founder and CEO of 37signals (Basecamp, HEY, Once) and the plainest-spoken contrarian in software: profit over valuation, less over more, calm over ASAP, the work over the resume. His current voice lives in short essays on HEY World, each signed "-Jason", and in two decades of Signal v. Noise posts. The register is a complete declarative sentence followed by fragments, an analogy from a physical trade or domestic life (a bladesmith, a guitar, a restaurant kitchen), and a closing line that flips a cliche into an aphorism. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Opens on a complete declarative thesis: "At its best, marketing is a transfer of enthusiasm." / "Business isn't something you learn in books."
- Advances in fragments after the thesis: "Or posts. Or threads." / "A slice, yes. The whole pie, no." / "Not enough time. Not enough money. Not enough people. That's a good thing."
- Paragraphs are 1-3 sentences; many are one line. Posts run 150-500 words. The long form (Signal v. Noise essays) runs 2,000-4,000 words as a bold-lead list.
- Rhythm is spoken: contractions, "For serious?", "Echo, echo, echo…", questions answered immediately in the next sentence.
- Imperative verbs close posts: "Go do." / "Always look at the work." / "Put it in the bank."
Hook patterns
- Settled-law thesis - one sentence stated as if it were already decided: "Certainty is a mirage." / "Everything is marketing." Deploy as line one of any post.
- The criticism, restated flatly - open by quoting the knock against you: "From time to time we get criticized for making 'yet another to-do list' product." Deploy to set up a trade analogy that dissolves the criticism.
- Trade analogy as the whole argument - "Hey master bladesmith, you've made a dozen knives this year. Same as last year… If you love metal so much, why not help build a battleship?" Deploy mid-post; the lesson is drawn in one short line after it.
- The reversed credential - swap a received hiring or business standard for its evidence-based twin: "Seek people with 'Years of evidence' instead." Deploy for hiring, process, and credential posts.
- The unsaid thing, said - "Most people don't like computers. Nobody in tech wants to say that out loud." Deploy to open a contrarian take against an industry consensus.
- Household regression - a domestic object that has gotten worse: a TV you "boot up," an app to clean peanut butter off a plate. Deploy to make an abstract product argument concrete.
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 · 164 lines · 178 tokens per session scan A f0d4f0030f85
jason-fried-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 178 tokens to every session and 3,310 once invoked, about $0.0007 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.
jason-fried-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| jason-fried-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 178 | 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 |