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 AskRoundtable/expert-skills --skill expert-kahnemangit clone --depth 1 https://github.com/AskRoundtable/expert-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/askroundtable/expert-skills/expert-kahneman)<a href="https://agentmods.dev/skills/askroundtable/expert-skills/expert-kahneman"><img src="https://agentmods.dev/badge/skills/askroundtable/expert-skills/expert-kahneman.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.03600 |
| Opus 5 | $0.00030 | $0.01800 |
| Sonnet 5 | $0.00012 | $0.00720 |
| Haiku 4.5 | $0.00006 | $0.00360 |
Grade A, and why
expert-kahneman 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 8d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Module: Daniel Kahneman (Behavioral Economics & Cognitive Biases)
Encodes Daniel Kahneman's thinking patterns for use with expert-engine.
When to Load
Load this module when facing:
- Evaluating the quality of a decision process (not just the outcome)
- Detecting cognitive biases in plans, forecasts, or narratives
- Calibrating overconfident predictions and project estimates
- Understanding why good people make systematically bad judgments
- Designing processes to reduce predictable errors
Specific Triggers:
- "Why did we all agree that was a good idea?"
- "Our forecast was way off again — what happened?"
- "I feel very confident, but maybe I shouldn't be"
- "How do we improve our decision process?"
- "I think I'm being rational, but something feels off"
Problem Framing (What → Why):
What-layer questions that arrive here often:
- "Why did we all agree on a bad idea?" → Why-layer: "Which System 1 substitution happened — what easier question did the group actually answer instead?"
- "Our forecast was way off — what happened?" → Why-layer: "Did we use the outside view and a reference class, or did Planning Fallacy and WYSIATI construct an inside-view story?"
- "I feel very confident about this decision" → Why-layer: "Is that confidence calibrated to evidence quality, or is Cognitive Ease making a familiar narrative feel true?"
When the user presents a What question, ask:
"Let's run a bias audit first: which cognitive system was driving this — the fast, pattern-matching System 1 or the slow, deliberate System 2? What's the outside view base rate, and how far has WYSIATI pulled us from it?"
Domain Boundaries
Core Domain (High Confidence): Kahneman's framework excels at auditing decision quality and detecting systematic cognitive errors.
- Cognitive bias identification and classification
- Forecast calibration and planning fallacy correction
- Decision audit (were we thinking correctly, not just did we get lucky?)
- Consumer psychology and nudge design
- Investment and financial decision quality
What ships with it
7 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.
- 8d ago First seen · 336 lines · 59 tokens per session scan A 36c8c372c79e
expert-kahneman is a skill published in the GitHub repository AskRoundtable/expert-skills (51 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 3,600 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
thinking-partner
A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly. Use this skill whenever a user says "help me think through X", "challenge my thinking", "what am I missing", "apply mental models to this", "play devil's advocate"…
thinking-toolkit
A toolkit of 30 decision-making, problem-solving, systems-thinking, and communication models, plus a /logic mode that audits an argument's validity. This skill should be used when a user names a specific model, or describes a situation that calls for one: framing or reframing a problem, comparing options, setting…
blindspot-check
Checks a big decision for blind spots against a catalogue of 95 cognitive biases before the user commits. Use when the user is about to make or has just justified a major life decision and wants to be checked for self-deception — buying a house, relocating, signing a long lease or contract, quitting or taking a job…
council
Evidence-bound multi-agent council for high-stakes decisions. Scout uses last30days, Advocate and Skeptic debate, Fact Checker uses deep-research Quick mode. Delivers ranked options with #1 marked, dissent preserved, and the condition that would flip the verdict. Use when user says council this, /council, run the…
munger-mental-models
A structured decision-analysis toolkit based on Charlie Munger's mental models from multiple academic disciplines.
reflect
Think through any decision — code, business, personal — and get a straight answer. Fires on "reflect on X", "start from first principles", "reflect"; AND fire it YOURSELF, unprompted, whenever the work hits a choice whose undo cost exceeds a bad day (architecture, dependencies, pricing, public commitments, people) or…