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 fatihguner/foreman --skill thinking-fast-and-slowgit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/thinking-fast-and-slow)<a href="https://agentmods.dev/skills/fatihguner/foreman/thinking-fast-and-slow"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/thinking-fast-and-slow/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/fatihguner/foreman/thinking-fast-and-slow"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/thinking-fast-and-slow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00095 | $0.03092 |
| Opus 5 | $0.00048 | $0.01546 |
| Sonnet 5 | $0.00019 | $0.00618 |
| Haiku 4.5 | $0.00010 | $0.00309 |
Grade A, and why
thinking-fast-and-slow 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 6d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Thinking, Fast and Slow
The human mind is simultaneously the most sophisticated decision-making instrument ever developed and a deeply unreliable narrator of its own reasoning. That paradox sits at the centre of Daniel Kahneman's work: the very cognitive machinery that enables entrepreneurs to spot opportunities in ambiguity is the same machinery that systematically misleads them about probability, risk, and the quality of their own judgments. Kahneman, a psychologist who won the Nobel Prize in Economics, spent decades demonstrating that rationality is not the default setting of the human brain -- it is an effortful exception. For founders making high-stakes decisions under uncertainty, understanding the architecture of their own thinking is not a philosophical luxury. It is a competitive necessity.
The Framework
Kahneman's model divides cognition into two distinct systems, each with its own operational characteristics, strengths, and failure modes.
System 1 and System 2
| Dimension | System 1 (Fast) | System 2 (Slow) |
|---|---|---|
| Speed | Instantaneous, automatic | Deliberate, effortful |
| Awareness | Operates below conscious threshold | Requires focused attention |
| Capacity | Parallel, high-throughput | Serial, limited bandwidth |
| Energy cost | Low | High (depletes with use) |
| Error profile | Systematic biases, predictable mistakes | Logical but lazy -- often endorses System 1 |
| Strengths | Pattern recognition, intuition, rapid assessment | Analysis, planning, complex calculation |
| Triggers | Familiar situations, emotional stimuli | Novel problems, explicit instructions to "think carefully" |
The critical insight is not that System 1 is bad and System 2 is good. Rather, most people -- including experienced executives -- dramatically overestimate how often System 2 is actually engaged. System 2 is cognitively expensive, and the brain defaults to System 1 wherever possible.
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.
- 6d ago First seen · 189 lines · 95 tokens per session scan A 7edfae8c3214
thinking-fast-and-slow is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 7d ago), licensed MIT. It adds 95 tokens to every session and 3,092 once invoked, about $0.0005 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 2026-09-06.
Other skills, from other repositories
learn
Knowledge compiler. Extracts patterns, decisions, and anti-patterns from completed campaigns and evolve cycles, then compiles them into structured wiki pages that integrate with existing knowledge rather than appending isolated files. Implements flush→compile→lint pipeline. Auto-triggered by /postmortem and /evolve…
zapier-demo
Walk a new user through setting up their first Zapier action and running it live — the smallest possible win. Asks what app they use, recommends one read action to enable, guides them to mcp.zapier.com to add it, then demonstrates it working in the same chat. Use when the user asks "show me how Zapier works", "set up…
mindtrain
Configure a private MindTrain instance, query its knowledge catalog, create user-approved training domains and knowledge points from AI dialogue or local reference libraries, and run persistent conversational training through Trainer MCP. Use when the user configures MindTrain, asks what domains or topics exist…
s4h-economics-coordination
Diagnoses collective action failures, public goods problems, and why individually rational behaviour produces collective irrationality. Triggers: 'collective action problem', 'tragedy of the commons', 'free rider', 'everyone is acting in their own interest but the result is bad for all', 'why won't people contribute'…
s4h-mindset-growth
Applies Carol Dweck's growth mindset research as a practical methodology — the actual mechanics, not the motivational poster version. Use when you're treating failure as evidence about your identity, avoiding challenges because of what failure would mean, comparing yourself to others in a way that deflates rather than…
s4h-mindset-positive
Applies positive psychology as a rigorous practice — not pop-psychology positivity. Use when you want to build flourishing, diagnose what dimension of wellbeing is underdeveloped, understand what makes life feel meaningful or hollow, or identify why you're not thriving despite the absence of obvious problems.…