black-swan

black-swan is a skill for Claude Code, Codex from deciqAI/knowledge-skills. It costs 125 tokens per session (2,189 once invoked), scanned A, original, MIT.

A way to examine rare events that fall outside normal expectations but can cause extreme damage. It also covers why such events often seem predictable only after they happen.

In plain words
What is it for?
Use it to stress-test strategies and portfolios, examine catastrophic failures, question normal-distribution assumptions, and identify risks hidden by confident forecasts.
Why use it?
It exposes the danger of relying on models or past experience that underestimate extreme outcomes. This is especially useful when someone treats a low probability as impossible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to stress-test strategies and portfolios, examine catastrophic failures, question normal-distribution assumptions, and identify risks hidden by confident forecasts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deciqai/knowledge-skills/black-swan
Install

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.

Any agent
npx skills add deciqAI/knowledge-skills --skill black-swan
Clone the repo
git clone --depth 1 https://github.com/deciqAI/knowledge-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for black-swan

README.md
[![agentmods](https://agentmods.dev/badge/skills/deciqai/knowledge-skills/black-swan/github.svg)](https://agentmods.dev/skills/deciqai/knowledge-skills/black-swan)
Your own site
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/black-swan"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/black-swan/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.

agentmods 80×15 button for black-swan

Your own site · 80×15
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/black-swan"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/black-swan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,189 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00125 $0.02189
Opus 5 $0.00063 $0.01094
Sonnet 5 $0.00025 $0.00438
Haiku 4.5 $0.00013 $0.00219

Measured 10d ago against content hash 5561ce362425, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

black-swan 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 10d 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.

black-swan/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Black Swan

Overview

Taleb (2007): a black swan is (1) outside all prior expectations, (2) extreme impact, (3) obvious in hindsight only. Many domains (markets, careers, tech) are Extremistan (power-law / fat-tail), yet most models assume Mediocristan (Gaussian / thin-tail) — underestimating tail risk by orders of magnitude. The Turkey Problem: 1000 days of feeding creates confidence; day 1001 is Thanksgiving.

Composes with antifragile, probabilistic-thinking, inversion, first-principles.

When to Use

Use when: a risk model assumes normality in a fat-tailed domain; "never happened in N years" dismisses tail risk; strategy assumes stable environment; you're constructing a retrospective narrative; stress-testing against extreme scenarios; someone says "fat tails / Taleb / narrative fallacy / turkey problem"; a thesis rests on a one-directional trend like "AI demand can only go up," AI-capex payoff, or concentrated mega-cap / AI-bubble exposure.

Not when: domain is genuinely Mediocristan; "black swan" is being used to excuse a foreseeable planning failure.

Coaching Novices (Adaptive Front Door)

  • Engine mode: user has a concrete case → run The Process directly.
  • Coach mode: user is unfamiliar or has no concrete case → guide step by step.

In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.

  1. One-line: some domains have rare events that dominate everything (markets, careers, tech); models assuming "normal" distributions miss them — and we always invent stories afterward that make them look predictable.
  2. Check fit: genuinely thin-tailed domain (heights, commutes)? Point elsewhere.
  3. Elicit the real situation — what decision or system are we auditing?

[WAIT — do not advance until user responds]

  1. One question at a time: is this Extremistan or Mediocristan? What's the tail-survival design? What narrative am I constructing post-hoc?

[WAIT — do not advance until user responds]

  1. Close: name the specific tail-event preparation — not prediction — they've uncovered.

[WAIT — do not advance until user responds]

Read the full file on GitHub · 133 lines

Files

What ships with it

4 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.

Changes

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.

  1. 10d ago First seen · 133 lines · 125 tokens per session scan A 5561ce362425

Subscribe to this mod's changes

black-swan is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 125 tokens to every session and 2,189 once invoked, about $0.0006 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

invoice-chase

Runs collections on late invoices: builds an aging ladder (current/30/60/90+), assigns each invoice a rung on an escalation sequence with ready-to-send emails — friendly nudge, firm reminder with late-fee mention, final notice — plus a phone script, tone rules that preserve the relationship, a chase log, and…

alebgl77/claude-inc · 0 tokens

plan-payroll

Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…

alebgl77/claude-inc · 0 tokens

review-contract

Clause-by-clause contract review — inventories key clauses (term, termination, liability cap, indemnity, IP, payment, confidentiality, governing law, auto-renewal), flags deviations from market-standard positions with RED/YELLOW/GREEN severity and verbatim quotes, drafts redline language, and sets negotiation…

alebgl77/claude-inc · 101 tokens

tax-prep

Organizes tax season — an organizer, not tax advice: a document checklist by category (income, expenses, assets, payroll, prior filings), an expense-category sweep that flags plausibly missed deductions in generic jurisdiction-agnostic categories, a quarterly-estimate calendar template, a clean handoff pack for the…

alebgl77/claude-inc · 0 tokens

audit-support

Gets the books audit-ready: builds the PBC (prepared-by-client) list by area, drafts walkthrough narratives for key cycles (revenue, purchases, payroll), matches auditor samples to support, prepares tie-out schedules, tracks open items with owners and due dates, and drafts responses to findings. Use when the user says…

alebgl77/claude-inc · 101 tokens

financial-statements

Builds a full statement set — P&L, balance sheet, and indirect cash flow — from a trial balance or transaction export, mapping accounts to a standard chart and proving every tie-out in code. Use when the user says 'build a P&L from this trial balance', 'turn this export into financials', 'I need a balance sheet for…

alebgl77/claude-inc · 97 tokens