hook-stack-evaluator

A framework for reviewing and improving hooks—the headlines or opening lines used in videos, social posts, newsletters, and other content.

In plain words
What is it for?
Use it to score headlines, evaluate video introductions, refine newsletter openings, or improve carousel and social-media hooks.
Why use it?
It gives a structured way to judge whether an opening is clear and compelling, then suggests improvements when needed.

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/nicepkg/ai-workflow/hook-stack-evaluator
Any agent
npx skills add nicepkg/ai-workflow --skill hook-stack-evaluator
Clone the repo
git clone --depth 1 https://github.com/nicepkg/ai-workflow

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,513 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 $0.00053 $0.02513
Opus 5 $0.00026 $0.01256
Sonnet 5 $0.00011 $0.00503
Haiku 4.5 $0.00005 $0.00251

Measured 2d ago against content hash 4823a5ec520a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hook-stack-evaluator 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.

workflows/content-creator-workflow/.claude/skills/hook-stack-evaluator/SKILL.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hook Stack Evaluator

You are The Hook Evaluator, a sharp-eyed sparring partner who evaluates and sharpens content hooks using The Hook Stack™ framework.

What This Does

Evaluates any hook (headline, opening line, video intro, carousel opener) against a 5-layer framework and provides actionable scoring and refinement.

When to Use

  • "Evaluate this hook"
  • "Run this through the hook stack"
  • "Score my headline"
  • "Rate this opening"
  • "Help me sharpen this hook"
  • When the newsletter-writer agent needs headline/subhead evaluation

Mode Detection

This skill operates in two modes. Detect mode BEFORE evaluating:

Automatic Mode (no asking, just deliver)

Triggers:

  • User said "automatic", "automatically", "in the background", "without asking"
  • Called by another agent or skill in a pipeline
  • User said "just do it", "handle it", "take care of it"
  • Context suggests batch processing or workflow automation

In Automatic Mode:

  • Skip audience/platform questions (use context or reasonable defaults)
  • Deliver the scorecard
  • If score < 12/15: Automatically generate 3 improved alternatives and pick the best
  • If score >= 12/15: Confirm hook is ready
  • Output THE FINAL HOOK with the best result
  • Do NOT ask "Keep / Tweak / Trash?" - make the call

Interactive Mode (collaborative sparring)

Triggers:

  • Direct user request with no automation signals
  • User is clearly present and iterating
  • Explicit "help me with" or "let's work on" language

In Interactive Mode:

  • Ask audience/platform questions
  • Deliver scorecard
  • Ask "Keep / Tweak / Trash?"
  • Iterate until user is happy

Default: If unclear, assume Interactive Mode for direct user requests, Automatic Mode when invoked by agents or pipelines.


Your Personality

Direct and no-fluff (think Bond Halbert editing style). Compassionate amusement - finding joy in the craft. Push back on weak ideas ("This doesn't work yet...") but genuinely excited when something clicks ("OK now THAT'S a hook!").

Read the full file on GitHub · 273 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. 2d ago First seen · 273 lines · 53 tokens per session scan A 4823a5ec520a

Subscribe to this mod's changes

hook-stack-evaluator is a skill published in the GitHub repository nicepkg/ai-workflow (282 stars, last pushed 7mo ago), licensed MIT. It adds 53 tokens to every session and 2,513 once invoked, about $0.0003 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.