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 vasilyu1983/AI-Agents-public --skill foundations-behavioral-economicsgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/foundations-behavioral-economics)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/foundations-behavioral-economics"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/foundations-behavioral-economics/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/vasilyu1983/ai-agents-public/foundations-behavioral-economics"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/foundations-behavioral-economics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 173 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00046 | $0.07731 |
| Opus 5.5 | $0.00018 | $0.03092 |
| Sonnet 5.5 | $0.00009 | $0.01546 |
| Haiku 4.5 | $0.00005 | $0.00773 |
Grade A, and why
foundations-behavioral-economics 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 15d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavioral Economics Foundations
Read each primitive's misuse boundary before applying it. The disclosure test is an ethical screen, not a legal definition: a technique that embarrasses the team on disclosure needs redesign even if it is lawful.
When to Apply
Apply behavioral-economics when:
- User-facing decision surface — pricing page, onboarding default, churn flow, retention nudge
- Habit-formation or cue-preservation in redesigns
- Loss-aversion / framing matters and downside is concrete
- Choice architecture — defaults, decoys, ordering, anchoring
- Conversion or activation experiment design where biases are exploitable ethically
Skip and use simpler alternatives when:
- Decision is between two AI systems or backend strategies (no human in the loop) — use foundations-decision-theory
- Causal "did the nudge work?" question — use foundations-causal-inference to measure
- Strategic multi-actor pricing — use foundations-game-theory (Bertrand, Vickrey)
- The proposed pattern requires deceiving the user about real value — fails the ethical gate; redesign, don't nudge
- Audience or market context is unknown — biases are not universal; lift bands won't generalise
- The required lift is larger than the evidence can support — diagnose the offer, audience, and friction before assuming framing can close the gap
Quick Reference
Each primitive has a full playbook: Definition / When to use / Misuse boundary / Inputs / Outputs / Failure modes / Worked example / Sources. Grades are explained in Expert Judgment.
| # | Primitive | Core Effect | When to Use | Grade |
|---|---|---|---|---|
| 1 | Prospect Theory | Gains and losses are not mirror images; framing shifts choice | Pricing copy, offer framing, upgrade messaging | A (direction) |
| 2 | Loss Aversion | Loss framing can shift choices; magnitude varies by task, stakes, and elicitation method | Churn prevention, trial expiry, feature removal messaging | B |
| 3 | Anchoring | First number shown distorts all subsequent judgments | Pricing pages, salary negotiation, discount presentation | A (direction) |
| 4 | Defaults | People disproportionately stick with pre-set options | Onboarding, opt-in/out choices, plan pre-selection | A for enrolment-type, low-effort choices; B elsewhere. Organ donation is not an A case: in a 2025 PNAS Nexus panel of opt-out switches, deceased-donor rates rose a non-significant +7% and living-donor rates fell 29% (crowding out). Pooled evidence undecided after correction — see nudge-calibration.md |
| 5 | Social Proof | People infer correct action from others' behavior | Sign-up pages, review placement, usage statistics | B |
| 6 | Scarcity | Limited availability increases perceived value | Inventory counts, time-limited offers, waitlists | B |
| 7 | Hyperbolic Discounting | Present bias: immediate rewards are disproportionately preferred | Free trials, commitment devices, annual vs monthly pricing | A (direction) |
| 8 | Mental Accounting | People categorize money differently depending on source and label | Bundling, gift cards, credit framing, sunk-cost effects | B |
| 9 | Choice Architecture | How choices are presented alters which option is selected | Option ordering, menu design, default pre-selection | C for "choice overload" specifically (mean effect ≈0, Scheibehenne et al. 2010); B for ordering/default effects generally |
| 10 | Dual-System Cognition | Two cognitive modes with different speed/effort profiles influence which levers work | Copy tone, complexity of CTA, trust signals | B — a descriptive heuristic, not a literal neural dichotomy |
| 11 | Decoy Effect / Asymmetric Dominance | A dominated option shifts preference toward its dominator | Pricing tier design, plan comparison tables | C — fragile outside stylized numeric stimuli (Frederick, Lee & Baskin 2014; Yang & Lynn 2014: 11/91 reliable) |
| 12 | Habit Loop | Stable cue → routine → reward becomes automatic with repetition | Daily/recurring usage, retention beyond week 4, durable behavior change | A (direction); no fixed weeks-to-automaticity number — see the fixed-weeks trap below |
| 13 | Reinforcement Schedules | Schedule (FR/VR/FI/VI), not just reward, governs acquisition and resistance to extinction | Streaks, rewards, gamification, reactivation; auditing existing reward systems | B |
| 14 | Cognitive Load & Working Memory | Working memory holds ~4 novel chunks; extraneous load suppresses informed choice | Forms, dashboards, alerts, error displays, consent flows, onboarding step count | A |
| 15 | Context-Dependent Retrieval | Behaviors are bound to the cues present at encoding; performance can weaken when context shifts | Migrations, redesigns, cross-surface continuity, dormant-user reactivation | B — direction reliable in meta-analysis (Smith & Vela 2001), moderated by "outshining" from non-contextual cues; the flagship Godden & Baddeley-style replication failed (Murre 2021 + 2022 addendum) |
| 16 | Implementation Intentions | User-endorsed if-then plans bind a specific cue to a specific response, supporting goal completion | Goal-pursuit features, onboarding into habit-forming behavior, transition-state re-anchoring | B — outcome-specific effects; publication-bias adjustment reduces the overall estimate (Sheeran et al. 2024; see evidence notes below) |
What ships with it
28 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.
- agents/openai.yaml 372 B
- assets/templates/behavioral-economics/01-prospect-theory.md 6.2 KB
- assets/templates/behavioral-economics/02-loss-aversion.md 5.6 KB
- assets/templates/behavioral-economics/03-anchoring.md 4.9 KB
- assets/templates/behavioral-economics/04-defaults.md 5.5 KB
- assets/templates/behavioral-economics/05-social-proof.md 4.9 KB
- assets/templates/behavioral-economics/06-scarcity.md 5.6 KB
- assets/templates/behavioral-economics/07-hyperbolic-discounting.md 6.3 KB
- assets/templates/behavioral-economics/08-mental-accounting.md 5.9 KB
- assets/templates/behavioral-economics/09-choice-architecture.md 7.1 KB
- assets/templates/behavioral-economics/10-dual-system.md 6.2 KB
- assets/templates/behavioral-economics/11-decoy-effect-asymmetric-dominance.md 8.1 KB
- assets/templates/behavioral-economics/12-habit-loop.md 8.5 KB
- assets/templates/behavioral-economics/13-reinforcement-schedules.md 8.2 KB
- assets/templates/behavioral-economics/14-cognitive-load-working-memory.md 8.4 KB
- assets/templates/behavioral-economics/15-context-dependent-retrieval.md 8.4 KB
- assets/templates/behavioral-economics/16-implementation-intentions.md 8.5 KB
- assets/templates/behavioral-economics/README.md 12 KB
- data/sources.json 51 KB
- learnings.consolidated.md 608 B
- learnings.md 1.2 KB
- references/composition-recipes.md 12 KB
- references/formal-theory-map.md 2.5 KB
- references/local-validation.md 2.8 KB
- references/nudge-calibration.md 6.1 KB
- references/patterns-scenarios-traps.md 7.7 KB
- references/primitives-overview.md 11 KB
- references/regulatory-context.md 6.4 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.
- 15d ago Changed · +1 lines 9f94c303da71
- 22d ago Changed · -220 lines · -2 tokens per session a6d1b18b963f
- 1mo ago Changed · +4 lines 536c79c88d6f
- 1mo ago First seen · 463 lines · 48 tokens per session scan A c909173e54c6
foundations-behavioral-economics is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (101 stars, last pushed 12d ago), licensed MIT. It adds 46 tokens to every session and 7,731 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
teach
Explain a body of work plainly so a person actually understands it. Runs the how and why skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
atlas-onboard
Generate onboarding documentation — what this project does, how to set up locally, where things live, key decisions, how to deploy. Written for day-one engineers who know nothing. Use when asked for "onboarding docs", "new engineer guide", "how to get started", or "developer setup".
continuum-quickstart
Get a Continuum agent up and running — Python 3.13 venv, infra via continuum up, smallest possible BaseAgent + AgentRunner example. Invoke when the user asks "how do I start", "set up Continuum", "run my first agent", or is at the very beginning of a project.
read-papers
Finds the latest research papers on a specific topic, summarizes their core contributions, and explains complex methodology in plain English.
summarize-podcast
Extracts transcripts from podcasts or videos and synthesizes actionable takeaways.
aetox-teach
สอนคนใช้ Aetox — ทำอะไรได้บ้างในคำที่คนเข้าใจ ห้องไหนไว้ทำอะไร ห้าอย่างที่คนใหม่ต้องรู้ และวิธีสอนด้วยการลงมือทำงานจริงของเขาแทนการบรรยาย · อ่านเมื่อผู้ใช้ถามว่าแอปนี้ทำอะไรได้ ถามวิธีใช้ หรือเพิ่งเปิดครั้งแรก.