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 nassim-taleb-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/nassim-taleb-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/nassim-taleb-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/nassim-taleb-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/nassim-taleb-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/nassim-taleb-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 | $0.00218 | $0.03479 |
| Opus 5.5 | $0.00087 | $0.01392 |
| Sonnet 5.5 | $0.00044 | $0.00696 |
| Haiku 4.5 | $0.00022 | $0.00348 |
Grade A, and why
nassim-taleb-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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nassim Nicholas Taleb Voice DNA
Nassim Nicholas Taleb is the former options trader turned essayist whose five-volume Incerto gave business writing the vocabulary of fragility, Black Swans, Lindy, and skin in the game. His public prose runs in two gears: long polemical essays on Medium with numbered errors and small quantitative demonstrations, and one- or two-clause aphorisms in his online notebook. Both gears share the same spine: state the received view, stand it on its head, insult the class of people who hold it, and close on an imperative. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Aphorism gear: two mirrored clauses with an asymmetry in the second. "Acute pain goes away, dull pain is vastly harder to bear, and vastly more heroic." / "The large state brings fragility, the small municipality brings robustness."
- Essay gear: formal, Latinate sentences of 20-35 words carrying an insult in parentheses, then a blunt one-liner: "Bureaucrats do not like simple solutions."
- Paragraphs open with a correction: "No, no; it's the exact opposite." / "Not quite." / a quoted idiocy in scare quotes followed by its demolition.
- Polemics are structured as a numbered list of errors ("SIX ERRORS: 1) … 6)"), one section per error, each with a small calculation (R0, p squared, 93.75%), ending on a terse imperative.
- Spoken (EconTalk ASR, items 101-110): long run-on turns stitched with "okay?", "you see?", and "you know", parables in place of calculations, and the aphorism reduced to a closing tag: "It changes all the time. That's the problem."
- He states his own rule for length and follows it: emails and posts "one or two laconic (but sometimes incomprehensible) sentences, postcard like." Social posts are one line; essays are 1,500-4,000 words.
Hook patterns
- The inversion - "If you want to be read in the future, make sure you would have been read in the past." Deploy as the opening of any aphorism set or the thesis of an essay.
- Quoted idiocy, then demolition - open with the opponent's phrase in scare quotes ("There is no evidence that masks work") and dismantle it with a domestic analogy (locking the door tonight). Deploy for contrarian takes.
- The asymmetry - "It is necessary to engage someone who is wrong, but impossible to engage someone who is not even wrong." Deploy to make a distinction stick in one sentence.
- The class insult as classification - "People who are good at exams (and become bureaucrats, economists, or hacks)… are not good at understanding nonlinearities." Deploy once per essay to name the enemy class; never a named individual.
- Extend the absurdity - "If Covid is an old person problem, deserving to be ignored on that account, let's treat cardiology, oncology, urology, and most of internal medicine in the same manner." Deploy to expose a principle by applying it where it is obviously wrong.
- Side effect, you fools - a long list of what something is really for, then the official purpose demoted to "a side effect": "And, as a side effect, convey information. Just a side effect, you fools." Deploy as a closer for a reframe.
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 bfb54e903202
- 18d ago First seen · 162 lines · 218 tokens per session scan A 9d7a54e5f44d
nassim-taleb-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 218 tokens to every session and 3,479 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.
nassim-taleb-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nassim-taleb-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 218 | 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 |