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/cdeistopened/skill-stack/hook-and-headline-writingnpx skills add cdeistopened/skill-stack --skill hook-and-headline-writinggit clone --depth 1 https://github.com/cdeistopened/skill-stackWrote 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/cdeistopened/skill-stack/hook-and-headline-writing)<a href="https://agentmods.dev/skills/cdeistopened/skill-stack/hook-and-headline-writing"><img src="https://agentmods.dev/badge/skills/cdeistopened/skill-stack/hook-and-headline-writing.svg" alt="Measured on agentmods" 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 | $0.00072 | $0.04164 |
| Opus 5 | $0.00036 | $0.02082 |
| Sonnet 5 | $0.00014 | $0.00833 |
| Haiku 4.5 | $0.00007 | $0.00416 |
Grade A, and why
hook-and-headline-writing 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.
How it starts
The opening of the file, as written. The whole thing — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hook and Headline Writer
Create hooks and headlines that stop the scroll and compel action using systematic frameworks, not guesswork.
Purpose
80% of content performance comes from the hook. This skill provides the frameworks to craft headlines that capture attention and drive engagement - for any industry, any platform, any content type.
Core Philosophy: Generate volume (10+ options), then select best using proven criteria. The first option is rarely the best option.
When to Use This Skill
- Writing newsletter subject lines that get opens
- Crafting social media thread hooks that stop the scroll
- Creating LinkedIn post first lines that compel "see more"
- Optimizing headlines for blog posts or articles
- Generating multiple hook variations for A/B testing
Pairs well with: anti-ai-writing (for humanizing headlines), voice style skills (for brand-specific tone)
Key Principles
The 3-Sentence Rule for Social Hooks
- Maximum 3 sentences for social media hooks
- First sentence MUST be short
- Each sentence's goal: get reader to the next
The 25% Rule
How to allocate time on any content:
- 25% ideation (identifying what to say)
- 25% hook/headline (crafting how to say it)
- 50% body content
Volume → Selection
- Generate 10+ variations minimum
- Select best using systematic criteria (not gut feel)
- The first option is rarely the best option
Story = Problem + Goal + Path
This equation equals value. Use it to identify what transformation your hook promises.
The 3-Phase Workflow
Phase 1: Generate Hook Ideas (Ideation)
Goal: Identify the core benefit, transformation, or insight your hook will promise
Step 1: Use the "Start Questioning" Method
Ask who/what/where/when/why/how about your topic. Then dig deeper by asking multiple times on the same answer.
Example:
- Topic: Productivity systems
- What? "What is the system?" → Time-blocking with deep work periods
- Why? "Why does it work?" → Eliminates context switching
- Why (deeper)? "Why does that matter?" → You get 3x output in half the time
- How? "How do people fail at this?" → They schedule too many blocks
- Impact angle discovered: "The counterintuitive key to time-blocking: schedule LESS"
What ships with it
9 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.
- references/10-commandments-checklist.md 22 KB
- references/headline-formulas-library.md 17 KB
- references/hook-types-expanded.md 10 KB
- references/ideation-process.md 13 KB
- references/output-formats.md 11 KB
- references/power-words-library.md 15 KB
- references/README.md 5.2 KB
- references/sticky-sentence-techniques.md 14 KB
- references/thread-hook-templates.md 17 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.
- 4d ago First seen · 509 lines · 72 tokens per session scan A cd1e30e8dd23
hook-and-headline-writing is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 4,164 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.
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.
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.
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.
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.
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…