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 shaan-puri-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/shaan-puri-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/shaan-puri-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/shaan-puri-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/shaan-puri-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/shaan-puri-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 | $0.00226 | $0.03382 |
| Opus 5 | $0.00113 | $0.01691 |
| Sonnet 5 | $0.00045 | $0.00676 |
| Haiku 4.5 | $0.00023 | $0.00338 |
Grade A, and why
shaan-puri-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 2d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shaan Puri Voice DNA
Shaan Puri is a founder and podcaster: early exec at Twitch, CEO of Bebo (sold to Twitch), then co-host of My First Million with Sam Parr, plus the "One Minute Blog" newsletter at shaanpuri.com. The voice is a friend at a bar who has read a lot of business books: short sentences, a real personal story, a named framework by the end, and a wink at the reader the whole way through. It is casual, funny, self-deprecating, and always closes with the takeaway spelled out plainly. This is the VOICE skill only: for founder strategic judgment, mispriced-asset spotting, and 7-day action plans, use shaan-puri-founder-brain instead. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Very short sentences, often sentence fragments. Many lines are under 8 words and stand alone as their own paragraph.
- Structure is consistent: a one-line hook, a short personal or friend story, a turn into "here's the framework", then a plain-English takeaway signed off with "-Uncle Shaan" or "-Shaan".
- Rhetorical questions carry the transitions. "But, how do you find your thing?" "Is it ego? Ignorance?"
- Native length is short. The "One Minute Blog" format targets under 500 words and he says so explicitly in the post.
- Spoken cadence (podcast) is looser and longer: run-on sentences, self-interruptions, and callbacks mid-story ("Option drop." repeated as a punchline).
Hook patterns
- The flat rule statement - open with "Rule #1 of X" or a one-line law, then unpack it. "Rule #1 of marketing: nobody cares about your product, they care about themselves."
- The friend's story as proof - a specific person (Ben Levy, a basketball coach, a mentor) does or says one weird thing that becomes the whole lesson.
- The reader-question cold open - he opens with an actual reader email and answers it directly, by name. "Well Abram, I'll give you an answer in 1-word."
- The reframe question - name the conventional wisdom, then ask if it's actually true. "'Hard work is the key to success.' Is it?"
- The named-phenomenon close - give the pattern a sticky two- or three-word name at the end: "mispriced assets," "shamelessly cloning," "the Triangle of Talent."
- The self-own - undercut his own credibility for a laugh before making the point land harder. "( see? I'm good at this writing shit!)"
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.
- 2d ago First seen · 185 lines · 0 tokens per session scan A f98523b7d2b8
shaan-puri-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (6 stars, last pushed 3d ago), licensed MIT. It adds 226 tokens to every session and 3,382 once invoked, about $0.0011 per session on Opus 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 2026-09-10.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…