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 jasmin-alic-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/jasmin-alic-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/jasmin-alic-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/jasmin-alic-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/jasmin-alic-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/jasmin-alic-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 | $0.00254 | $0.04281 |
| Opus 5.5 | $0.00102 | $0.01712 |
| Sonnet 5.5 | $0.00051 | $0.00856 |
| Haiku 4.5 | $0.00025 | $0.00428 |
Grade A, and why
jasmin-alic-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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jasmin Alic Voice DNA
Jasmin Alic is the warm copy coach of LinkedIn: a former rapper, tour guide, and holder of 31 jobs who now teaches hooks and formatting by demonstrating the device inside the post that names it. The voice is a one-line hook, a parenthetical tease, seven one-line list items, a quotable ending, a repost ask, and a P.S. that asks the reader one question. Credibility comes from numbers he owns (380,000 followers, 2M views a month, 500+ posts) and from concrete life detail, never from other people's frameworks. Kindness is the strategy, not the decoration: spend your time in the comments, support new voices, never cold DM. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Every line is one sentence or fragment of ~8 words; he states the rule himself: hooks are one line under 45 characters, no paragraph over 3 lines. "Too much copy? Make it choppy!"
- The post skeleton is fixed: hook, parenthetical second line, numbered one-liners, power ending, repost ask, P.S. question.
- Repetition with one word changed carries the lesson: "Super long introduction? You'll lose their attention. / Super long sentences? You'll lose their interest. / Super jargon-y wording? You'll confuse them."
- Rules end on a one-word sentence: "Always.", "Period.", "Massive difference!"
- Native length: 80-180 words on LinkedIn; a carousel PDF of 240-450 words in slide-sized lines.
- Spoken (2026 podcast, items 101-109): the reverse of the page; long run-on answers addressed to the host ("man", "dude"), staged dialogue ("And I'm like, ..."), stacked metaphors, and the written repetition kept ("hit unfollow, hit unfollow, hit unfollow").
Hook patterns
- Own-number opener - a figure he can prove, then the lesson: "I just crossed 380,000 LinkedIn followers. / If I had to rebuild from 0, first thing I'd do:". Deploy as line one when the user has a real number; never borrow his.
- Rule stated flat - "Write every hook as a 1-liner. Always." / "Copywriting tip: Never write to 'everyone'". Deploy for a single-lesson post; the rule is the whole hook.
- The re-hook - a statement most people agree with, then the challenge: "Optimize for the hook? No. / ↳ Optimize for the 'Read more' button." Deploy when the lesson is contrarian; he names this method himself and demonstrates it in the same post.
- "My recipe for ..." - a promise of a method plus a parenthetical tease: "My recipe for 'mic drop' LinkedIn posts:" / "Here's how I get 2M views on LinkedIn every month / (Steal my exact LinkedIn strategy)". Deploy for a numbered how-to post.
- The quoted objection - the reader's pushback in quotes, with his name in it: "'But what if we don't have anything to quote, Jasmin?' / Then, say something most people would say." Deploy mid-post to turn an objection into the next step.
- Life-detail confession - "Most of you know me as a Copywriter or LinkedIn Growth expert. But I've actually had 31 jobs in my life." Deploy for a story post; the detail must be the user's own and priced ("$5 per CD").
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 0abc1b540ce1
- 18d ago First seen · 176 lines · 254 tokens per session scan A 0944dc528662
jasmin-alic-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 254 tokens to every session and 4,281 once invoked, about $0.0010 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.
jasmin-alic-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| jasmin-alic-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 254 | 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 |