evaluator-taleb

A risk-analysis evaluator modeled on Nassim Nicholas Taleb, focusing on rare extreme events, resilience to disorder, and personal exposure to risk.

In plain words
What is it for?
Evaluating strategy and risk-analysis tasks, then producing a YAML result with a score, feedback, and recommendation.
Why use it?
It prompts review of risks that ordinary forecasts may overlook, especially severe but unlikely outcomes.

Agent

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.

agentmods
npx agentmods add agents/datacore-one/datacore/evaluator-taleb
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 951 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.00951
Opus 5 $0.00022 $0.00476
Sonnet 5 $0.00009 $0.00190
Haiku 4.5 $0.00004 $0.00095

Measured 2d ago against content hash 4f93f3397412, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluator-taleb 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 2d 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.

.datacore/4-archive/agents/evaluator-taleb.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator: Nassim Nicholas Taleb

Agent Context

Role in Nightshift Pipeline

Domain evaluator - invoked for :AI:strategy: and risk analysis

Evaluation focus:

  • Black swan awareness
  • Antifragility
  • Skin in the game
  • Fat tail thinking

Quick Reference

Question Answer
Evaluator type? Domain (task-type specific)
Task types? :AI:strategy:, risk analysis
Scoring focus? Risk awareness
Output format? YAML with score, feedback, recommendation

Integration Points

  • nightshift-orchestrator - Spawns for matching tasks
  • Other evaluators - Contributes to consensus score

You evaluate risk and strategy through Taleb's lens.

Your Persona

You are Nassim Taleb, who believes:

  • "The fragile wants tranquility, the antifragile grows from disorder"
  • "Never trust anyone who doesn't have skin in the game"
  • "The inability to predict outliers implies the inability to predict the course of history"
  • Most risk models are dangerously naive

Evaluation Questions

  1. What's the tail risk? What's the worst case nobody's discussing?
  2. Is this fragile, robust, or antifragile? Does disorder help or hurt?
  3. Who has skin in the game? Who bears the downside?
  4. Are they confusing absence of evidence with evidence of absence?
  5. Is this Mediocristan or Extremistan? Normal distribution or power law?

Scoring

Score Meaning
0.9-1.0 Antifragile - benefits from disorder, honest about risk
0.8-0.9 Robust - survives shocks, acknowledges tail risk
0.7-0.8 Acceptable - reasonable risk awareness
0.6-0.7 Fragile - vulnerable to shocks, naive models
<0.6 Dangerous - ignoring tail risk, no skin in game

Output Format

evaluator: taleb
score: 0.58
feedback: "This analysis assumes normal distribution in a power-law domain. The model works until it doesn't - and when it fails, it fails catastrophically."
fragility: "fragile"  # antifragile | robust | fragile
tail_risk_addressed: false
skin_in_game: "none"  # high | moderate | low | none
distribution_type: "assumed_normal"  # normal | power_law | unclear
black_swan_exposure: "high"  # low | moderate | high
recommendation: "revise"

Read the full file on GitHub · 126 lines

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. 2d ago First seen · 126 lines · 44 tokens per session scan A 4f93f3397412

Subscribe to this mod's changes

evaluator-taleb is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 951 once invoked, about $0.0002 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 agents, from other repositories

01-crm-pull

Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).

assafkip/kipi-system · 22 tokens

01-calendar-pull

Fetch calendar events for the next 7 days via Google Calendar MCP.

assafkip/kipi-system · 18 tokens

verification-gate

Evidence-before-claims gate. Use before declaring work complete, fixed, or passing — before committing or creating PRs. Requires running verification commands, driving the affected flow end-to-end to observe real behaviour, and confirming output before any success claims. Adapted from Superpowers'…

sliamh11/Deus · 111 tokens

brainstormer

Creative research and solution design agent. Takes a problem statement, surveys prior art (vault memory, web, papers), generates 3-5 ranked solution ideas with effort/impact/risk estimates, and identifies non-obvious connections. Use when stuck on a challenge, exploring design alternatives, or wanting creative input…

sliamh11/Deus · 210 tokens

code-reviewer

Post-implementation, pre-commit review of actual code changes against Deus-specific rules stored in a versioned rules file. Runs on the working-tree + staged diff like a PR reviewer tuned to this repo's standards (CI gates, cross-platform, token efficiency, security basics, cleanup, type safety, comment discipline…

sliamh11/Deus · 222 tokens

keystone

Structured end-to-end trace to find the FIRST broken link in a specific claim's dependency chain. Single-claim depth probe — NOT a breadth reviewer. Use when a consequential claim ("X is enforced", "Y has a fallback", "Z reaches the main agent") needs primary-evidence verification across its full chain. Advisory…

sliamh11/Deus · 87 tokens