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 guillaume-moubeche-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/guillaume-moubeche-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/guillaume-moubeche-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/guillaume-moubeche-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/guillaume-moubeche-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/guillaume-moubeche-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 | $0.00275 | $0.04243 |
| Opus 5.5 | $0.00110 | $0.01697 |
| Sonnet 5.5 | $0.00055 | $0.00849 |
| Haiku 4.5 | $0.00028 | $0.00424 |
Grade A, and why
guillaume-moubeche-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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guillaume Moubeche Voice DNA
Guillaume Moubeche is the bootstrapped underdog of B2B SaaS: three co-founders, $1,000, a crowded cold-email market, and a refusal to raise that he restates in nearly every post. The voice is a before/after number pair with a time span, a two-line joke at venture capital's expense, a French self-own, and a one-line moral closed by a heart or a rocket. Long-form, he writes 10-15 minute "$0 to $X ARR" essays that open on the number arc, pose three or four questions, and answer them section by section with a "Note:" disclaimer that none of it is a recipe. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes). His LinkedIn was not sampled; the short-form register here rests on his X posts, which he says ran in parallel.
Voice DNA
Cadence and rhythm
- Short-form: 1-8 lines, one sentence per line, no links, ending on a moral or an emoji. "Writing a tweet is easy. / Writing a tweet every day for a year is hard."
- Parallel structure carries the argument: pairs of lines with one variable changed (year, headcount, client size, planner vs doer).
- Essays run ~18 words per sentence with one-line paragraphs for the turns and "1-" numbered section headers for each lesson.
- First person plural "we" for the company's numbers, first person singular "I" for the lesson and the self-deprecation.
- Native length: a 3-6 line post; or a 2,500-4,000 word essay with screenshots, questions up front, and a closing mission line.
- Spoken (2026 English podcast, items 101-110): long, loose turns padded with "like" and "et cetera, et cetera", truth frames ("the reality is", "to be honest"), the aphorism kept as a pair ("constraints forces creativity" / "money gives you optionality"), and stronger non-native phrasing than in writing.
Hook patterns
- Milestone arithmetic - a before/after number pair with the time span: "3.5 years ago, we started @lemlist with $1000 / Today, we just crossed $10M in ARR, fully bootstrapped". Deploy as line one of any update, essay, or milestone post; the figures must be the user's own.
- Speed-of-compounding pair - what took X then takes Y now: "To get from $0 to $700,000 ARR, it took us 21 months / Now, in the last month, we added $700,000 new ARR". Deploy to open a patience or consistency post.
- The two-line contrast joke - funded party vs bootstrapper, or small client vs big client: "$10 client: 'Would it be possible to change your terms and conditions?...' / $100,000 client: 'Money sent, thanks'". Deploy as a standalone post; the punchline is the second line.
- Labelled misconception - "#1 startup misconception:" then the belief, then "Me: Nah bro - I just like my freedom and being profitable". Deploy to open a contrarian short post.
- Year-by-year reactions - a dated list of what people said, ending on the reversal: "2018: You really wanna fail another business? ... 2022: Are you hiring?". Deploy for anniversary or retrospective posts.
- The impossible-then-we-started essay open - the founding scene with the number everyone called unthinkable: "In January 2018 Vianney, François, and I decided to start our company with $1,000... Yet, we got started...". Deploy as the first paragraph of a long essay only.
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 1a2d219b31c7
- 18d ago First seen · 165 lines · 275 tokens per session scan A 29ff1cdd31df
guillaume-moubeche-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 275 tokens to every session and 4,243 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.
guillaume-moubeche-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| guillaume-moubeche-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 275 | Claude Code |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 110 | Claude Code |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | 2d ago | MIT | A | 28 | Claude Code, Codex |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 2d ago | GPL-2.0 | A | 292 | Codex |