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 wdavidturner/product-skills --skill thinking-in-betsgit clone --depth 1 https://github.com/wdavidturner/product-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/wdavidturner/product-skills/thinking-in-bets)<a href="https://agentmods.dev/skills/wdavidturner/product-skills/thinking-in-bets"><img src="https://agentmods.dev/badge/skills/wdavidturner/product-skills/thinking-in-bets/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/wdavidturner/product-skills/thinking-in-bets"><img src="https://agentmods.dev/badge/skills/wdavidturner/product-skills/thinking-in-bets.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 | $0.00076 | $0.01074 |
| Opus 5 | $0.00038 | $0.00537 |
| Sonnet 5 | $0.00015 | $0.00215 |
| Haiku 4.5 | $0.00008 | $0.00107 |
Grade A, and why
thinking-in-bets 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 11d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking in Bets
What It Is
Thinking in Bets is a framework for improving decision quality by separating decisions from outcomes. The core insight: a good decision can have a bad outcome, and a bad decision can have a good outcome—luck is always involved.
Most people judge decisions by their outcomes (called "resulting"). This is backwards. You can only control the quality of your decision, not the outcome. Annie Duke, a professional poker player turned decision strategist, built this framework from poker, where you're forced to make decisions with incomplete information under uncertainty—exactly like business.
The key shifts:
- Move from "Was I right?" to "Was my thinking process good?"
- Move from "What happened?" to "What did I know at the time?"
- Move from implicit assumptions to explicit, testable beliefs
When to Use It
Use Thinking in Bets when you need to:
- Evaluate past decisions without outcome bias clouding judgment
- Make decisions under uncertainty where luck will influence results
- Improve team decision-making in meetings and planning
- Set up pre-mortems and kill criteria for projects
- Shorten feedback loops on decisions with delayed outcomes
- Reduce cognitive biases like overconfidence, hindsight bias, and sunk cost
- Run better meetings that surface true opinions, not groupthink
When Not to Use It
- The decision is trivial with low stakes
- You have perfect information (rare)
- You're looking for permission to take a risk you've already decided on
Patterns
Detailed examples showing how to apply Thinking in Bets correctly. Each pattern shows a common mistake and the correct approach.
Critical (get these wrong and you've wasted your time)
| Pattern | What It Teaches |
|---|---|
| resulting | Don't judge decisions by outcomes—judge by the process |
| implicit-vs-explicit | Make intuitions explicit so you can test and improve them |
| discover-discuss-decide | Separate discovery (async), discussion (meetings), and decisions |
| premortems-without-kill-criteria | Pre-mortems are useless without committed actions |
What ships with it
16 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.
- patterns/_template.md 460 B
- patterns/anchoring-in-groups.md 2.4 KB
- patterns/confirmation-bias.md 2.4 KB
- patterns/discover-discuss-decide.md 2.5 KB
- patterns/forecasting-ranges.md 2.6 KB
- patterns/hindsight-bias.md 2.6 KB
- patterns/implicit-vs-explicit.md 2.0 KB
- patterns/long-feedback-loops.md 2.6 KB
- patterns/mental-time-travel.md 2.4 KB
- patterns/nevertheless-leadership.md 2.5 KB
- patterns/overconfidence.md 2.2 KB
- patterns/premortems-without-kill-criteria.md 2.4 KB
- patterns/resulting.md 2.1 KB
- patterns/seeking-alignment.md 2.4 KB
- patterns/sunk-cost.md 2.4 KB
- references/thinking-in-bets-playbook.md 11 KB
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.
- 11d ago First seen · 97 lines · 76 tokens per session scan A eeef46c70215
thinking-in-bets is a skill published in the GitHub repository wdavidturner/product-skills (20 stars, last pushed 7mo ago), licensed MIT. It adds 76 tokens to every session and 1,074 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…