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 agentmods add skills/motion-creative/motion-creative-plugin/write-hooksnpx skills add Motion-Creative/motion-creative-plugin --skill write-hooksgit clone --depth 1 https://github.com/Motion-Creative/motion-creative-pluginWhat 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 | $0.00085 | $0.02826 |
| Opus 5 | $0.00043 | $0.01413 |
| Sonnet 5 | $0.00017 | $0.00565 |
| Haiku 4.5 | $0.00009 | $0.00283 |
Grade A, and why
write-hooks 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 2d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hook Writing Engine
Generate psychologically-driven hooks that capture attention in the first 1-3 seconds of paid social ads. Every hook is grounded in workspace performance data from Motion.
Phase 0: Orient
- Acknowledge: "I'll generate hooks grounded in what's actually converting in your account."
- Ask if missing: "Product, target persona, and pain point? Or should I pull these from your workspace data?" If any required input is ambiguous, ask — don't assume.
- Important distinction: Hooks that stop the scroll and hooks that convert are often different. After generating, note which hooks optimize for attention vs. which optimize for action.
- Connected workflow: After hooks, you can brief the full ad (
/build-brief) or analyze how existing hooks perform (/analyze-ad).
If the user provided product, persona, and pain point clearly, skip questions.
Core Principle
A hook is the tactical expression of a messaging angle at a specific awareness stage. Before writing hooks, understand what the audience already knows and feels.
Hook Sources
Pain points are the most reliable hook source. Start here before trying other angles. See references/hook-sources.md for the full breakdown.
6 categories of pain-based hook material:
- Emotional pain points (start here) — what keeps them stuck, worried, or frustrated
- Daily annoyances — small friction the audience lives with every day
- Embarrassing habits — what they do but don't talk about
- Silent frustrations — what they tolerate because they think it's just normal
- Protective beliefs — what they tell themselves to avoid having to change
- Self-awareness moments — the truth they already half-know but haven't admitted
When generating a set of hooks, mine at least 2-3 different source categories to ensure emotional variety.
Phase 1: Gather Inputs
1a. Parse Arguments
Extract from $ARGUMENTS:
- Product: What does it do?
- Pain or Desire: What specific need does it address?
- Persona: Who are you targeting? (life context, not just demographics)
--stage: Awareness stage (unaware, problem-aware, solution-aware, product-aware, most-aware). Default: generate across all stages.--format: Video or static. Default: video.--count: How many hooks. Default: 10.
What ships with it
4 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.
- 2d ago First seen · 251 lines · 85 tokens per session scan A f1901a2eb492
write-hooks is a skill published in the GitHub repository Motion-Creative/motion-creative-plugin (20 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 2,826 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…