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 peep-laja-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/peep-laja-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/peep-laja-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/peep-laja-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/peep-laja-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/peep-laja-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 | $0.00207 | $0.03302 |
| Opus 5 | $0.00103 | $0.01651 |
| Sonnet 5 | $0.00041 | $0.00660 |
| Haiku 4.5 | $0.00021 | $0.00330 |
Grade A, and why
peep-laja-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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peep Laja Voice DNA
Peep Laja built his authority the hard way: run the agency, run thousands of tests, watch which tactics actually move a number and which ones are cargo cult. Three companies later (CXL, Speero, Wynter) the voice has not softened into guru-speak. It is a founder-operator who distrusts opinion, distrusts "best practices," and will tell you your favorite tactic is worthless if the data says so. Where April Dunford's positioning voice is a patient consultant retelling a war story, Laja's is shorter, flatter, and quicker to declare something wrong outright. He does not warm the reader up. 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 declarative sentences, 6 to 18 words. Fragments are normal ("Nobody has that kind of time.").
- Opens on a flat claim or a rhetorical question aimed straight at the reader ("How would you do it?").
- Body stacks a numbered or dashed list almost immediately. He does not stay in prose for long.
- Paragraphs run one to three sentences. A single-sentence paragraph is common for emphasis.
- Native length varies hard by channel: a CXL post runs 600-1200 words, a LinkedIn post runs 80-200 words, a tweet is one idea in 2-4 lines.
Hook patterns
- The direct verdict - state the wrong belief and knock it down in the first line. "Working Hard Doesn't Matter If You Don't Know What You're Doing."
- The imagine-this scenario - put the reader in a specific hypothetical job and make them answer. "Let's say tomorrow you'll get fired... Now tell me how would you do it."
- The diagnostic quiz - your answer to a small scenario reveals whether you are an amateur or a pro. "Your answer will tell me everything about your optimization know-how."
- The two-person exchange - a short real dialogue, quoted, that makes the point better than explanation would. "Me: 'So what's the answer?' Him: 'I don't know, but all the data is in here.'"
- The reframe of a sacred term - take a widely loved concept (USP, best practices, working hard) and explain precisely why it stopped working.
- The numbered gap list - "Everything gets stale over time: - your talking points - ad creative - content format" then the fix in one line.
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 · 171 lines · 0 tokens per session scan A 2a516874b78a
peep-laja-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (6 stars, last pushed 3d ago), licensed MIT. It adds 207 tokens to every session and 3,302 once invoked, about $0.0010 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…