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 hooked-modelgit 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/hooked-model)<a href="https://agentmods.dev/skills/wdavidturner/product-skills/hooked-model"><img src="https://agentmods.dev/badge/skills/wdavidturner/product-skills/hooked-model/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/hooked-model"><img src="https://agentmods.dev/badge/skills/wdavidturner/product-skills/hooked-model.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 | $0.01132 |
| Opus 5 | $0.00038 | $0.00566 |
| Sonnet 5 | $0.00015 | $0.00226 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
hooked-model 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 10d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Hooked Model
What It Is
The Hooked Model is a framework for building products that create unprompted user engagement. The core insight: habit-forming products connect to internal triggers through a repeating cycle of trigger, action, reward, and investment.
When a product becomes a habit, users engage without external prompts. They don't need ads, emails, or notifications to come back. They return because the product has become their automatic response to an internal trigger like boredom, loneliness, uncertainty, or FOMO.
The key shift: Move from asking "How do we get users to open the app?" to asking "What internal trigger do we want to own, and how do we become the automatic response to it?"
When to Use It
Use the Hooked Model when you need to:
- Design features that drive repeat engagement (not just one-time use)
- Reduce dependency on external marketing to bring users back
- Improve retention and decrease churn through habit formation
- Understand why competitor products are so sticky (reverse-engineer their hooks)
- Create ethical engagement that genuinely improves users' lives
- Prioritize which features to build based on habit potential
- Increase customer lifetime value through deeper product integration
When Not to Use It
- The product is inherently infrequent (e.g., buying a house, annual insurance)
- Users should consciously evaluate each decision (e.g., financial trading, medical diagnosis)
- Habit formation would harm users rather than help them
- You want to manipulate users into behaviors against their interests
Patterns
Detailed examples showing how to apply the Hooked Model 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 |
|---|---|
| external-triggers-only | Products that rely only on notifications never form habits |
| action-too-hard | If the action requires effort, the habit loop breaks |
| predictable-rewards | Predictable rewards don't create craving; variable rewards do |
| no-investment | Without investment, users have no stake in returning |
| wrong-internal-trigger | Targeting the wrong emotion means the habit never sticks |
What ships with it
19 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/ability-before-motivation.md 2.2 KB
- patterns/action-too-hard.md 1.7 KB
- patterns/combining-reward-types.md 2.1 KB
- patterns/dark-patterns-vs-ethical.md 2.2 KB
- patterns/external-triggers-only.md 2.1 KB
- patterns/frequency-matters.md 1.9 KB
- patterns/habit-path-identification.md 2.3 KB
- patterns/investment-loads-next-trigger.md 2.0 KB
- patterns/manipulation-matrix.md 2.3 KB
- patterns/no-investment.md 1.9 KB
- patterns/predictable-rewards.md 1.9 KB
- patterns/rewards-of-the-hunt.md 2.1 KB
- patterns/rewards-of-the-self.md 2.1 KB
- patterns/rewards-of-the-tribe.md 2.0 KB
- patterns/stored-value-compounds.md 2.2 KB
- patterns/vitamin-vs-painkiller.md 2.0 KB
- patterns/wrong-internal-trigger.md 2.0 KB
- references/hooked-model-playbook.md 12 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.
- 10d ago First seen · 92 lines · 76 tokens per session scan A e106cb375f8b
hooked-model 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 1,132 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.