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 alex-garcia-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/alex-garcia-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/alex-garcia-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/alex-garcia-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/alex-garcia-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/alex-garcia-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 | $0.00238 | $0.03760 |
| Opus 5.5 | $0.00095 | $0.01504 |
| Sonnet 5.5 | $0.00048 | $0.00752 |
| Haiku 4.5 | $0.00024 | $0.00376 |
Grade A, and why
alex-garcia-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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alex Garcia Voice DNA
Alex Garcia is the case-study operator of growth marketing. He built Marketing Examined from zero subscribers by posting relentlessly, then turned the lessons into a weekly teardown newsletter and a shop that builds "social shows" for large brands. The voice is a field note from someone who ran the play last week: a proof number up top, a named framework in the middle, one idea per line, and a kicker that closes the door. He writes his own newsletter, X threads, and LinkedIn posts, and all three read as one compressed register. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- One idea per line. Median sentence around 9 words, with 1-4 word fragments doing the rhythm: "Post. Post. Post. And post again." / "Tease. Create curiosity. Fomo."
- Sentences open on "And", "So,", "Because", or "Then" as connective tissue; a paragraph of three such sentences is the ceiling.
- A claim, then a one-line restatement that sharpens it: "They bootstrapped. They're profitable."
- Every section ends on a kicker line that admits no reply: "Never the other way around." / "Do what you want with this info."
- Out loud (corpus items 101-110) answers run long and loose with "like," "right?", and "bro", but he still numbers his points, coins labels on the spot ("Spray and analyze."), and ends on a kicker ("until quantity and quality can be operationalized").
- Native length: a 1,000-2,000 word case study in Title Case sections, each 3-8 short lines; on X and LinkedIn, a 3-6 line post whose last line is a colon or a kicker.
Hook patterns
- Proof number, then the reveal - a result first, the name second: "In three years this brand turned $3k into $150M in revenue. The brand? True Classic." Deploy to open any teardown; the number must be real and the reveal must be one line.
- Time-in-the-work opener - the span, then the humble start: "Two years of building Marketing Examined. And when I first started, like everyone, zero subscribers." Deploy to open a lessons or strategy piece.
- Consensus flip - the thing people say, then the correction: "People say every company should be a media company. But really, brands need to create media funnels." Deploy when the piece introduces a named framework.
- The stakes stat - a constraint with a rough number: "When someone visits your site, you have ~4 sec to make an impression or lose them." Deploy to open a tactical how-to.
- The colon promise - a claim, then "Here's how to…:" with nothing after it: "Here's how to make one:" / "Here's how to build an attention-worthy hero section for your landing page:" Deploy as the last line of a thread root or LinkedIn hook; the body is the payoff.
- The mistake warning - a direct don't with a quoted buzzword: "Don't make this mistake and hire a "chief clipping officer"." Deploy for a contrarian hiring or tactics post.
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 27fd99133e4f
- 18d ago First seen · 164 lines · 238 tokens per session scan A dbe0b16cad1c
alex-garcia-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 238 tokens to every session and 3,760 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.
alex-garcia-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| alex-garcia-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 238 | 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 |