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 deciqAI/knowledge-skills --skill nudge-theorygit clone --depth 1 https://github.com/deciqAI/knowledge-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/deciqai/knowledge-skills/nudge-theory)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/nudge-theory"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/nudge-theory/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/deciqai/knowledge-skills/nudge-theory"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/nudge-theory.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 | $0.00135 | $0.02121 |
| Opus 5 | $0.00068 | $0.01060 |
| Sonnet 5 | $0.00027 | $0.00424 |
| Haiku 4.5 | $0.00014 | $0.00212 |
Grade A, and why
nudge-theory 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 9d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nudge Theory
Overview
People procrastinate on retirement savings, skip vaccine appointments, and leave privacy settings on dangerous defaults — not from ignorance, but because the choice environment works against them. Nudge theory (Thaler & Sunstein) treats choice architecture — defaults, framing, social norms, friction — as the decisive variable. A nudge alters behavior in a predictable way without forbidding options or changing economic incentives; it must be easy and cheap to avoid. The foundational result: switching 401(k) enrollment from opt-in to opt-out raised participation from ~49% to ~86% — a 37-point lift from changing only the default.
Composition: use status-quo-bias before nudge design to know where inertia points; use probabilistic-thinking to estimate effect size; use second-order-thinking to catch downstream consequences (e.g., a low default rate that anchors people).
When to Use
Apply when: (1) intent-action gap exists; (2) mandates or financial incentives are infeasible or unacceptable; (3) the choice environment can be redesigned; (4) you are setting defaults, opt-in/opt-out flows, or model-selection and data-sharing settings in an AI-native product where choice architecture steers millions of users amid rapid AI adoption and AI-native competition.
When NOT to use: gap is informational (educate first); deep values at stake; expert deliberate decision-makers (System 2); no defensible claim one outcome is better for the chooser.
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete behavior gap → run The Process directly.
- Coach mode: user is unfamiliar or has no concrete case → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- One-line what-it-is: a nudge is any small change to the environment — a default, a framing tweak, a social comparison — that steers people toward a better choice without forcing or paying them.
- Check fit against When to Use / When NOT to use. If the gap is informational, redirect to communication design.
- Elicit their real behavior gap. "We want users to engage more" is not a case; "63% never complete their first savings transfer despite signing up" is.
[WAIT — do not advance until user responds]
- Run The Process one step at a time — diagnose each EAST barrier before prescribing a mechanism.
[WAIT — do not advance until user responds]
- Close by naming the one nudge change most likely to close the gap, and the metric that would prove it worked.
[WAIT — do not advance until user responds]
What ships with it
3 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.
- 9d ago First seen · 123 lines · 135 tokens per session scan A e10e2db2a081
nudge-theory is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 135 tokens to every session and 2,121 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
edge-tts
Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
tianqi
A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.
cto-advisor
Records technical decisions that serve a business outcome: constraints, architecture options, build-or-buy tradeoffs, and a justified skill selection. Use when the CEO asks "which architecture fits", "should we build or buy", "which skill should this department use", or "review our technical plan".
compliance-check
Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…
plan-payroll
Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…