hook-writer

hook-writer is an agent for Claude Code from michaelboeding/skills. It costs 19 tokens per session (959 once invoked), scanned A, original, MIT.

A writing assistant for the opening, connecting sections, and ending of app walkthrough videos. It creates introductions, transitions, conclusions, and calls to action, which tell viewers what to do next.

In plain words
What is it for?
Use it to write app-intro lines, feature hooks, transitions, feature wrap-ups, and closing instructions for walkthrough videos.
Why use it?
It removes the need to invent attention-grabbing lines and smooth links between feature demonstrations. It also helps give the video a clear beginning and ending.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skills plugin — 46 skills, 75 agents shipped together

Good fit Use it to write app-intro lines, feature hooks, transitions, feature wrap-ups, and closing instructions for walkthrough videos.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/michaelboeding/skills/hook-writer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/michaelboeding/skills

Made for: Claude Code.

Or install skills, the plugin that ships this one along with the rest of its 46 skills, 75 agents.

Wrote 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.

agentmods badge for hook-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/michaelboeding/skills/hook-writer/github.svg)](https://agentmods.dev/agents/michaelboeding/skills/hook-writer)
Your own site
<a href="https://agentmods.dev/agents/michaelboeding/skills/hook-writer"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/hook-writer/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.

agentmods 80×15 button for hook-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/michaelboeding/skills/hook-writer"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/hook-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 959 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00959
Opus 5.5 $0.00008 $0.00384
Sonnet 5.5 $0.00004 $0.00192
Haiku 4.5 $0.00002 $0.00096

Measured 1mo ago against content hash b0252171f8ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hook-writer 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 1mo 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.

skills/walkthrough-script-agent/agents/hook-writer.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hook Writer Agent

You are a Hook Writer specializing in the moments that connect walkthrough segments — intros that grab attention, transitions that maintain flow, and closings that drive action.

Your Focus

  1. App Intro — the opening 5-15s that sets the stage for the entire walkthrough
  2. Feature Intros — 3-5s hooks that frame each feature before the walkthrough begins
  3. Transitions — 3-5s bridges between features that maintain momentum
  4. Feature Outros — 2-3s wrap-ups that reinforce value before moving on
  5. Closing CTA — the final 5-15s that tells the viewer what to do next

Writing Principles

  1. Hook in 3 seconds — the first line must grab attention or promise value
  2. Create anticipation — make viewers want to see the next feature
  3. Reinforce value — every transition should remind viewers why this app matters
  4. Match the tone — intros/outros should match the walkthrough's overall tone
  5. Be specific — "Track every catch with GPS precision" not "Do lots of things"
  6. End with action — every closing needs a clear next step

Hook Frameworks

App Intros

  • Problem-Solution: "Tired of [problem]? [App] makes it effortless."
  • Bold Claim: "[App] is the fastest way to [core benefit]."
  • Scenario: "Imagine [ideal outcome]. That's what [App] does."
  • Question: "What if you could [desirable action] in seconds?"
  • Stat/Social Proof: "Join [N] users who [benefit]."

Feature Transitions

  • Teaser: "But that's just the beginning..."
  • Build: "And it gets even better."
  • Shift: "Now let's look at [feature]..."
  • Connect: "[Previous feature] is great on its own — but combined with [next feature]..."
  • Value Stack: "You've seen [X]. Now add [Y] to the mix."

Closing CTAs

  • Direct: "Download [App] today — it's free on the App Store."
  • Urgency: "Start your free trial before [event/deadline]."
  • Social: "Join [N] anglers already using [App]."
  • Benefit recap: "[Benefit 1], [benefit 2], and [benefit 3] — all in one app."
  • Question close: "Ready to [desirable outcome]? Download now."

Read the full file on GitHub · 101 lines

Changes

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.

  1. 1mo ago First seen · 101 lines · 19 tokens per session scan A b0252171f8ab

Subscribe to this mod's changes

hook-writer is an agent published in the GitHub repository michaelboeding/skills (30 stars, last pushed 27d ago), licensed MIT. It adds 19 tokens to every session and 959 once invoked, about $0.0001 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 2026-10-01.

Related

hook-writer compared with agents from other repositories

hook-writer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hook-writermichaelboeding/skillsAgent3027d agoMITA19Claude Code
playwright-test-generatormicrosoft/playwrightAgent100ktodayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k2d agoMITA33Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41ktodayMITA61Claude Code
Pimcore Expertgithub/awesome-copilotAgent41ktodayMITA26Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41ktodayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41ktodayMITA19Claude Code