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 wes-kao-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/wes-kao-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/wes-kao-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/wes-kao-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/wes-kao-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/wes-kao-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 | $0.00223 | $0.03706 |
| Opus 5.5 | $0.00089 | $0.01482 |
| Sonnet 5.5 | $0.00045 | $0.00741 |
| Haiku 4.5 | $0.00022 | $0.00371 |
Grade A, and why
wes-kao-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 17d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wes Kao Voice DNA
Wes Kao writes the sentence you should have said. Her essays name a concept, stage two operators saying two versions of the same thing, ask which one adds more value, and then hand over the script: the line to stop using marked with a no sign, the line to use marked with a check. The voice is calm, declarative, and exacting, with the kindness located in the logic rather than the tone: if you save your recipient a mental step, you are doing a kind thing. She pre-empts the objection, scopes the claim, and closes with one thing to do today. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Calm, medium-length declaratives with plain verbs and few adjectives; the thesis gets its own one-line paragraph: "Rigorous thinking is where flimsy ideas go to die." / "Backstory scope creep is real."
- Short definitional sentences stack: "Being concise is about using an economy of words. It's maximizing your word 'real estate.' It's about density, not absolute length."
- Hypotheticals open with "Let's say..." and worked examples with "For example,"; the reader is addressed as "you" and occasionally as "Folks."
- The turn is a question the reader must answer: "Which operator do you think adds more value?" / "What do you think I mean?"
- Native length: a 1,200-2,500 word essay in Part I / Part II sections with a "Do this today" block; a 6-12 line LinkedIn post that compresses one framework into a numbered list.
- Spoken (items 101-110, one podcast), she opens with 'Yes, so' or a pet peeve ('One of my pet peeves is...', 'I really hate excessive formatting.'), names the concept ('blast radius', 'take the win'), and keeps the paired restatement ('you can't cut to the chase unless you know what the chase is'); sentences run 25-45 words with 'uh', 'um', and 'you know' left in.
Hook patterns
- The named concept as title - "Defensible, but not good" / "Observe, assert, and validate (OAV)" / "Start right before you get eaten by the bear." Deploy as the title and first line of any framework piece.
- Operator #1 versus Operator #2 - two people say two versions of the same ask; "Which operator do you think adds more value?" Deploy to open managing-up and communication essays.
- The Slack DM hypothetical - "Let's say I send you a Slack DM that says, 'Hey, this is a priority.' What do you think I mean?" Deploy to expose a vague habit before naming it.
- The flat distinction - "There is a difference between work that seems useful vs work that's actually useful." Deploy as a one-line thesis paragraph.
- The bear - a story cut to its last ten seconds ("We heard rustling around 11pm."), then "WHAT??", then the rule. Deploy in storytelling and concision content.
- The spiky claim with its reason - "Start with why has done more harm than good." followed immediately by why. Deploy for a contrarian take that is a thesis, not a stir.
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.
- 17d ago Changed · +1 lines 6cce6a2e928c
- 18d ago First seen · 171 lines · 223 tokens per session scan A 2d0465b27e4b
wes-kao-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 223 tokens to every session and 3,706 once invoked, about $0.0009 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.
wes-kao-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wes-kao-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 223 | 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 |