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 marcos-sponton/frameworks-as-skills --skill hookedgit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-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/marcos-sponton/frameworks-as-skills/hooked)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/hooked"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/hooked/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/marcos-sponton/frameworks-as-skills/hooked"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/hooked.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 | $0.00261 | $0.03026 |
| Opus 5 | $0.00130 | $0.01513 |
| Sonnet 5 | $0.00052 | $0.00605 |
| Haiku 4.5 | $0.00026 | $0.00303 |
Grade A, and why
hooked 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hooked
Nir Eyal's Hook Model is a four-phase framework for designing habit-forming products — products that bring users back repeatedly without relying on costly advertising or aggressive messaging. Eyal is a former Stanford GSB and Hasso Plattner Institute lecturer, behavioral design consultant, angel investor (Canva, Kahoot!, Eventbrite), and NYT bestselling author of Hooked: How to Build Habit-Forming Products (Portfolio, 2014), Indistractable: How to Control Your Attention and Choose Your Life (BenBella, 2019), and Beyond Belief (Portfolio, 2026). The model draws on BJ Fogg's Behavior Model, B.F. Skinner's variable reinforcement schedules, and behavioral economics to explain how products create loops — experiences that connect the user's problem to the product's solution with enough frequency to form a habit.
This skill captures both the supply-side framework (Hooked — how to design hooks) and the demand-side framework (Indistractable — how to resist unwanted hooks), because Eyal insists they are two sides of the same coin. It also includes the post-book evolution: how Eyal's thinking on tech ethics, personal responsibility, and belief systems has matured since 2014.
When this skill activates
Use this skill when the user is:
- Designing a new product's engagement loop and wants to apply behavioral design principles — not just "add notifications."
- Diagnosing why an existing product's retention or engagement is dropping — the Hook Model is a diagnostic tool, not just a design tool.
- Designing onboarding to convert new users into habitual users — using Eyal's Habit Test (identify habitual users → codify the habit path → modify onboarding to accelerate it).
- Evaluating whether a product's engagement design is ethical — the Manipulation Matrix (would I use this? does it improve the user's life?) is the test.
- Identifying the internal trigger that should drive their product — using the 5 Whys to dig from surface behavior to emotional root cause.
- Designing variable reward mechanics — and needs to understand the three types (Tribe, Hunt, Self) and why variability is the load-bearing word.
- Applying the Indistractable framework to manage their own distraction, design a team's focus practices, or help users manage attention.
- Analyzing competitors' engagement design through the lens of the Hook Model.
- Deciding whether behavioral design (Hooked) or personal habit formation (Atomic Habits) or micro-behavior design (Fogg) is the right framework for their situation.
What ships with it
12 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.
- evals/evals.json 8.4 KB
- examples/.gitkeep 0 B
- README.md 8.6 KB
- references/applications.md 8.3 KB
- references/author-live-sources.md 9.8 KB
- references/examples.md 11 KB
- references/heuristics.md 14 KB
- references/method.md 17 KB
- references/post-book.md 10 KB
- references/prompts.md 4.5 KB
- references/sources.md 7.2 KB
- references/voice-and-tone.md 9.6 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.
- 9d ago First seen · 94 lines · 261 tokens per session scan A 4b39533bc936
hooked is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 261 tokens to every session and 3,026 once invoked, about $0.0013 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 2026-08-31.
Other skills, from other repositories
web-design-reviewer
This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage…
design-explore
Explore 2-4 design options with pros/cons/criteria matrix before writing code. Use for L3-L4 tasks (refactors, architecture, new subsystems). Pairs with savedecision MCP tool.
awesome-design-md
Create a DESIGN.md style baseline BEFORE building UI. Use FIRST when no design draft exists — installs a proven visual style, then invoke frontend-design to implement. For borrowing a known product style, getting consistent typography/colors/spacing, or needing a fast visual starting point.
build-sdf-liquid-glass
Build lightweight SDF/canvas displacement glass with Vaso. Use for responsive refractive cards, no-WebGL fallbacks, many compact surfaces, or explicit SDF requests.
build-webgl-liquid-glass
Build production-ready GPU liquid-glass surfaces with liquid-gl for React or DOM UIs. Default for refractive cards, notifications, panels, GPU bevels, and WebGL glass.
kirby-panel-and-blueprints
Designs Kirby blueprints and Panel UI, including blueprint reuse/extends, programmable blueprints, and custom Panel fields/sections/areas. Use when changing the Panel experience or schema.