What is hook-retention-teardown?

A tool-guided analysis of a creator’s best and worst social-media video openings. It compares transcripts and pacing to identify patterns linked with viewer retention, meaning how long people keep watching.

Use it to compare top and bottom posts, study hooks and openings, measure speaking pace, and review first-person language or calls to action.

It replaces general advice with a comparison of the creator’s own successful and unsuccessful videos.

hook-retention-teardown — Skill for Claude Code and Codex by scrollmar

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.

Any agent

npx skills add scrollmark/socialgpt-mcp --skill hook-retention-teardown

Clone the repo

git clone --depth 1 https://github.com/scrollmark/socialgpt-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/scrollmark/socialgpt-mcp/hook-retention-teardown/github.svg)](https://agentmods.dev/skills/scrollmark/socialgpt-mcp/hook-retention-teardown)

Your own site

<a href="https://agentmods.dev/skills/scrollmark/socialgpt-mcp/hook-retention-teardown"><img src="https://agentmods.dev/badge/skills/scrollmark/socialgpt-mcp/hook-retention-teardown/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/scrollmark/socialgpt-mcp/hook-retention-teardown"><img src="https://agentmods.dev/badge/skills/scrollmark/socialgpt-mcp/hook-retention-teardown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,380 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.

Model	Per session	Once invoked
Fable 5.1	$0.00154	$0.01380
Opus 5	$0.00077	$0.00690
Sonnet 5	$0.00031	$0.00276
Haiku 4.5	$0.00015	$0.00138

Measured 12d ago against content hash 544070c74e1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hook-retention-teardown 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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/analyze.py, scripts/sgpt_lib.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/hook-retention-teardown/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hook & Retention Teardown

Find the language and pacing patterns that separate a creator's winners from their flops — so they learn what their own best hooks and openings do that their weak ones don't. This is the deterministic, transcript-level complement to qualitative hook advice: instead of vibes, you measure words-per-second, opener style, first-person language, and CTA placement, then show exactly where the top cohort diverges from the bottom.

This skill pairs with the SocialGPT MCP server (https://mcp.gpt.social/mcp). The MCP provides the data; this skill provides the deterministic analysis and a shareable report. If the SocialGPT tools below aren't available, the user needs to connect the MCP first: https://gpt.social/integrations/mcp

When to use

Trigger on requests like: "why do my best videos pop and others flop?", "what makes a good hook for me?", "compare my top and bottom posts", "what should my openings do?", "do a teardown of my hooks", "what do my winners do differently?"

Workflow

Confirm access. Make sure the SocialGPT MCP tools are connected. If list_videos isn't available, point the user to the connect page above and stop.
Find the winners and flops. Call:
```
list_videos(sort="top", limit=20)
```
Rank by metrics.views. Take the top ~5 and the bottom ~5. Exclude Instagram videos with views == 0 (Instagram hides reel plays, so a 0 there isn't a real flop).
Fetch each video's full analysis. For every selected video, call:
```
get_video_analysis(platform, post_id)
```
This returns the transcript, hooks, and suggested hooks the teardown needs.
- Right after ingest this may return {"status": "pending"} — that's not an error. Wait ~20s and retry. Only include a video once its analysis is ready (it has a transcript).
- Skip any video that still has no transcript after retrying; it just won't count toward the teardown.

Read the full file on GitHub · 122 lines

Files

What ships with it

3 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.

12d ago First seen · 122 lines · 154 tokens per session scan A 544070c74e1c

Subscribe to this mod's changes

hook-retention-teardown is a skill published in the GitHub repository scrollmark/socialgpt-mcp (10 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 1,380 once invoked, about $0.0008 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 2026-08-31.

Analytics and metrics Marketing and SEO ai-agents chatgpt claude creator-tools cursor

9router-video

Generate videos via 9Router /v1/videos/generations using xAI Grok Imagine (grok-imagine-video). Async job flow - submit, poll requestid until done, download MP4. Use when the user wants to create, generate, or render a video, text-to-video (txt2vid), or image-to-video.

decolua/9router · 74 tokens

9router-web-fetch

Fetch URL → markdown / text / HTML via 9Router /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.

decolua/9router · 67 tokens

9router-web-search

Web and X search via 9Router /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik. Use when the user wants to search the web, find articles, or search public X posts.

decolua/9router · 74 tokens

9router-chat

Chat / code generation via 9Router using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through 9Router.

decolua/9router · 63 tokens

9router-embeddings

Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.

decolua/9router · 66 tokens

9router-stt

Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.