hook-methodology

hook-methodology is a skill for Claude Code, Codex from DV0x/creative-ad-agent. It costs 43 tokens per session (3,022 once invoked), scanned A, original, MIT.

A method for finding advertising opening lines, called hooks, directly in a research document. It covers ten hook types, such as questions, surprising statistics, and customer proof, without adding unsupported claims.

In plain words
What is it for?
Use it to create opening lines for Meta ads and other conversion-focused campaigns. It helps turn research into different angles for stopping attention and encouraging clicks.
Why use it?
It reduces guesswork when writing ads by tying each proposed hook to evidence already found in the research. This helps keep campaign copy grounded in what the brand has actually said or delivered.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/dv0x/creative-ad-agent/hook-methodology
Any agent
npx skills add DV0x/creative-ad-agent --skill hook-methodology
Clone the repo
git clone --depth 1 https://github.com/DV0x/creative-ad-agent

Made for: Claude Code, Codex.

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-methodology

README.md
[![agentmods](https://agentmods.dev/badge/skills/dv0x/creative-ad-agent/hook-methodology.svg)](https://agentmods.dev/skills/dv0x/creative-ad-agent/hook-methodology)
Your own site
<a href="https://agentmods.dev/skills/dv0x/creative-ad-agent/hook-methodology"><img src="https://agentmods.dev/badge/skills/dv0x/creative-ad-agent/hook-methodology.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,022 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.03022
Opus 5 $0.00022 $0.01511
Sonnet 5 $0.00009 $0.00604
Haiku 4.5 $0.00004 $0.00302

Measured 4d ago against content hash 8ccd130cd56d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hook-methodology 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 4d 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.

agent/.claude/skills/hook-methodology/SKILL.md · 453 lines

How it starts

The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research-First Hook Methodology

Every hook must be traceable to a specific research element. No invention—only discovery.

Core Philosophy

Research first. Every hook has a SOURCE.

The best hooks aren't constructed from templates.
They're extracted from what the brand has already proven, said, or delivered.

If you can't point to where it came from in the research,
it's invention. Invention is weak. Discovery is strong.

The 10 Hook Types

Before extracting, know what you're looking for:

Attention Hooks (Stop the Scroll)

Type Purpose Example Pattern
Question Challenge assumption "What's the biggest mistake you're making?"
Surprising Stat Unexpected number "90% of banks reject self-employed applicants"
Pattern Interrupt Break expectations Unexpected statement that contradicts normal
Controversial Challenge belief Question something everyone accepts
Direct Address Call out situation "Self-employed? Bank said no?"

Desire Hooks (Drive Clicks)

Type Purpose Example Pattern
Social Proof Credibility through numbers "16,000+ Canadians switched and saved"
Problem-Solution Name pain, offer relief Pain statement → Solution hint
Contrast Show gap "[Bad thing] vs. [Better thing]"
FOMO/Urgency Scarcity, pressure Limited time, competitive pressure
Curiosity Tease hidden info "What your bank isn't telling you"

Step 1: EXTRACT (Read EVERY Section)

Read agent/files/research/{brand}_research.md

You MUST extract from EVERY section. No exceptions.


FROM: The Offer

Extract:

  • Core promise (what they sell)
  • Key numbers (rates, coverage, speed, capacity)
Example:
"AI-powered mortgage brokerage, 350+ lenders, rates from 4.19%, 24-48 hour approvals"

FROM: Key Value Props

Extract:

  • Each differentiator as a potential hook angle
  • What makes them different from competitors

Read the full file on GitHub · 453 lines

Files

What ships with it

2 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.

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. 4d ago First seen · 453 lines · 43 tokens per session scan A 8ccd130cd56d

Subscribe to this mod's changes

hook-methodology is a skill published in the GitHub repository DV0x/creative-ad-agent (114 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 3,022 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens