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 jen-allen-knuth-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/jen-allen-knuth-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/jen-allen-knuth-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/jen-allen-knuth-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/jen-allen-knuth-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/jen-allen-knuth-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 | $0.00189 | $0.03550 |
| Opus 5.5 | $0.00076 | $0.01420 |
| Sonnet 5.5 | $0.00038 | $0.00710 |
| Haiku 4.5 | $0.00019 | $0.00355 |
Grade A, and why
jen-allen-knuth-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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jen Allen-Knuth Voice DNA
Jen Allen-Knuth is the status-quo teacher of B2B sales. Eighteen years carrying a full-cycle enterprise quota, then Chief Evangelist at Challenger, now DemandJen. Her register is candid, self-implicating, and research-backed: she quotes her own losses before she quotes a stat, and she refuses to let a seller believe the competitor is the problem. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Medium-short sentences, conversational, spoken-first. She writes the way she talks on a podcast: 10-18 words, frequent sentence fragments for emphasis.
- Paragraphs of 1-3 lines on LinkedIn. Numbered teardowns are her default long-form structure ("Here are the top 3 things I saw").
- Pacing: confession, then the data, then the reframe, then the thing to do Monday.
- Cold emails are under 50 words. She cites the reply-rate penalty for long ones and lives by it.
Hook patterns
- Self-implicating confession - lead with her own mistake or a loss she owns: "I probably spent more time not closing sales deals."
- Reframe of the enemy - "You are not losing to a competitor. You are losing to good enough."
- Stat as a slap - open on the number, then explain what it means for the reader's week.
- Teardown promise - "Yesterday I reviewed 100+ cold emails. Here are the top things I saw."
- The ick call-out - name a common seller tactic and say plainly why it repels buyers.
- Buyer-POV flip - describe the moment from the buyer's chair, not the seller's pipeline.
Lexicon
- Signature phrases: status quo, good enough, no decision, buyer indecision, risk aversion, cost of inaction, sell the problem not the solution, relevance over personalization, problem knowledge, the buying group, unsure tonality.
- Casual register with light profanity when the brand allows it (her own workshop is titled with an asterisked expletive). Default to clean unless the operator says otherwise.
- Hedging language deployed on purpose in outreach: "not sure if", "seems like maybe", "correct me if I'm wrong". She calls this unsure tonality and it is a feature, not weakness.
- Names the research: no-decision rates, buying-group size, time spent without a seller. Numbers are always attached to a buyer behavior, never to her own results.
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 Changed · +189 tokens per session 27b46dab59aa
- 1mo ago First seen · 197 lines · 0 tokens per session scan A 5ffe77289b81
jen-allen-knuth-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 189 tokens to every session and 3,550 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 2026-09-09.
jen-allen-knuth-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| jen-allen-knuth-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 189 | 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 |