Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add AI-Answer/ContentRepurposeSystem/plugin install content-repurpose-systemWrote 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/ai-answer/contentrepurposesystem/yt-titles)<a href="https://agentmods.dev/skills/ai-answer/contentrepurposesystem/yt-titles"><img src="https://agentmods.dev/badge/skills/ai-answer/contentrepurposesystem/yt-titles.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 5.1 | $0.00107 | $0.01668 |
| Opus 5 | $0.00053 | $0.00834 |
| Sonnet 5 | $0.00021 | $0.00334 |
| Haiku 4.5 | $0.00011 | $0.00167 |
Grade A, and why
yt-titles scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Title Generator
Generate YouTube title options for your channel by analyzing what's already working and applying those patterns to new content.
Why this approach works
YouTube titles aren't random — channels develop signature patterns that their audience responds to. By looking at your actual performance data (not generic "YouTube tips"), the titles this skill generates are grounded in what's proven to work for YOUR audience specifically. This matters because a title style that crushes it for a coding tutorial channel might flop on a business channel, even in the same niche.
Workflow
Step 1: Pull your channel performance data
Run the channel performance script to get your recent top performers:
python "${CLAUDE_PLUGIN_ROOT}/skills/yt-titles/scripts/channel_performance.py" --months 3 --count 30
This returns your videos from the last 3 months sorted by views, with views/day, engagement ratio, and like ratio. The views/day metric is especially important — it normalizes for upload date so a video posted yesterday isn't penalized against one from 2 months ago.
Step 2: Analyze your title patterns
Look at the top 10 performers and identify:
- Hooks: What opening words/phrases pull people in? (e.g., "I built...", "Stop...", "This...", "How I...")
- Structure: What format do the titles follow? (e.g., "Hook + specific outcome", "Question format", "Number + result")
- Length: What character count range do top titles fall in?
- Specificity signals: Do they mention tools by name? Time frames? Dollar amounts? Results?
- Emotional triggers: Curiosity gaps, contrarian takes, urgency, authority?
Also note patterns in the BOTTOM performers — what to avoid.
Step 3: Scout the competition
See what titles already exist for the same topic:
Optional step. This uses a separate
yt-searchhelper script that does not ship with this plugin. If it isn't installed, skip it — Steps 1, 2, and 4 (your own performance data + pattern analysis + generation) are the core of this skill and work on their own.
What ships with it
1 file 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.
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.
- 8d ago First seen · 135 lines · 107 tokens per session scan A 7594a884966c
yt-titles is a skill published in the GitHub repository AI-Answer/ContentRepurposeSystem (13 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,668 once invoked, about $0.0005 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
wechat-article-writer
A Chinese-language content-creation workflow for public-account and social-media writing. It supports article drafting, cover images, illustrations, process diagrams, style analysis, and adapting writing to selected styles.
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
ernie-image
Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or strong instruction following for complex multi-object scenes. Also supports denoise-based image-to-image refine (NOT…
qwen-image-edit
Build Qwen Image Edit workflows covering model loading, conditioning, LoRAs, prompt patterns, and XY plot testing.
rgthree
Configure and author rgthree-comfy nodes — Fast Groups Bypasser/Muter (group toggles), Power Lora Loader, Context/Context Big, Seed, Any Switch. Use when a workflow contains rgthree nodes, when asked to add stage/section toggles or an A/B switch, when stacking LoRAs, or when an rgthree node needs configuring. Covers…
wan-t2v-video
Build WAN 2.2 Text-to-Video workflows. Dual hi-lo models, lightning LoRAs, VACE modules, and KSamplerAdvanced two-pass.