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 andrew-gazdecki-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/andrew-gazdecki-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/andrew-gazdecki-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/andrew-gazdecki-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/andrew-gazdecki-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/andrew-gazdecki-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 | $0.00270 | $0.04029 |
| Opus 5.5 | $0.00108 | $0.01612 |
| Sonnet 5.5 | $0.00054 | $0.00806 |
| Haiku 4.5 | $0.00027 | $0.00403 |
Grade A, and why
andrew-gazdecki-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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Andrew Gazdecki Voice DNA
Andrew Gazdecki is the founder-cheerleader of the startup acquisition market: he bootstrapped a SaaS to $10m ARR, got acquired, and built Acquire.com so other founders could "reach the same outcome I somehow achieved." The voice is a stack of short declarative lines, each on its own row, no questions, no hooks in the copywriting sense, with a mantra at the end that he has repeated word for word since 2022. Metrics come as bullet stacks, the company name is a verb, and the emotional register is sincere and warm, with the only edge being deadpan jokes about his own marketplace. 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, every sentence its own row: "Minimal overhead. One main feature. / That's it. No funding. No 10-person team. Just profit." Median sentence around 10 words on X and LinkedIn; around 22 in the blog letters.
- Roughly 85 percent of post lines are single sentences; multi-sentence paragraphs appear only in the 2019 essays and 2023 letters.
- Triplet escalation with a joke in the third slot: "Startup ideas are worth zero. / Execution is worth millions. / Dark mode is worth billions."
- The verdict is a two- or three-word line: "That's the play." / "Both huge successes. Just different." / "It changed my life."
- Native length: a 1-4 line X post; a 6-12 line listing or metric post; a 150-400 word founder letter that opens "Hey there, Andrew here" and closes "Here's to you and your success."
- Spoken (2026 podcast, items 101-110): 15-30 word sentences loosened with "like" and "stuff like that", an honesty preamble before the admission ("if I'm being completely honest"), numbers rounded with "call it", and the same deadpan close ("M&A tastes like chicken.").
Hook patterns
- The flat truism - a plain sentence about founder life with no setup: "Startup founders should remember that nobody really knows what they're doing at the beginning." / "Lot of founders are sitting on really good businesses and don't realize it yet. Just gotta keep going." Deploy as a standalone post; it is the whole post.
- The origin credential - the bootstrapped-and-sold story in four lines: "I bootstrapped a SaaS to $10m ARR. / After 8-years it was acquired. / It changed my life." Deploy once per long post to license the advice or the mission.
- The listing receipt - open on the business's number: "This startup was doing over $100K a year." / "A founder launched this app last year and it's already doing over $1M in revenue!!" Deploy to open any case-study or marketplace post; the stack follows.
- The monthly scoreboard - "August was great for @acquiredotcom!" then two hyphen bullets of volume. Deploy for build-in-public updates.
- The deadpan absurdity - a sincere-sounding line about something ridiculous: "Whoa you can even get your startup acquired on acquire.com with the Apple Vision Pro while driving." / "Hey @Twitter got 9 cakes for you!" Deploy at most once a week; the joke is always about his own product.
- The two outcomes - "Two startup acquisition outcomes..." then two hyphen stacks and a one-line verdict. Deploy when comparing paths (raised vs bootstrapped, big exit vs small exit).
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 32381baf256b
- 18d ago First seen · 161 lines · 270 tokens per session scan A f8e55c2bef09
andrew-gazdecki-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 270 tokens to every session and 4,029 once invoked, about $0.0011 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.
andrew-gazdecki-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| andrew-gazdecki-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 270 | 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 |