agent-bank: Skill for OpenCode

.opencode/skill/youtube-rl-tracker/SKILL.md

youtube-rl-tracker is a skill for OpenCode from different-ai/agent-bank. It costs 28 tokens per session (1,447 once invoked), scanned A, original, MIT.

A Notion-based tracker for recording YouTube video results and comparing choices such as thumbnails, titles, and opening hooks. The results are reviewed manually to identify patterns for future videos.

In plain words
What is it for?
Use it to log views, click-through rate, and audience retention after publishing a video. Compare stronger and weaker videos, then apply the findings to future thumbnails, titles, and topics.
Why use it?
It turns video performance into a record that can be compared over time instead of relying on guesswork. This helps show which presentation choices are associated with better results.

Skill for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: mentions OpenCode.

This is different-ai/agent-bank's own configuration. It tells OpenCode how to work on agent-bank itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-bank configures →

Reuse

Borrowing it

Nothing to install: this file belongs to different-ai/agent-bank. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/different-ai/agent-bank/main/.opencode/skill/youtube-rl-tracker/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/different-ai/agent-bank

Made for: OpenCode.

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 youtube-rl-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/different-ai/agent-bank/youtube-rl-tracker/github.svg)](https://agentmods.dev/skills/different-ai/agent-bank/youtube-rl-tracker)
Your own site
<a href="https://agentmods.dev/skills/different-ai/agent-bank/youtube-rl-tracker"><img src="https://agentmods.dev/badge/skills/different-ai/agent-bank/youtube-rl-tracker/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.

agentmods 80×15 button for youtube-rl-tracker

Your own site · 80×15
<a href="https://agentmods.dev/skills/different-ai/agent-bank/youtube-rl-tracker"><img src="https://agentmods.dev/badge/skills/different-ai/agent-bank/youtube-rl-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,447 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.01447
Opus 5 $0.00014 $0.00724
Sonnet 5 $0.00006 $0.00289
Haiku 4.5 $0.00003 $0.00145

Measured 10d ago against content hash a6a33644c5aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

youtube-rl-tracker 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 10d 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.

.opencode/skill/youtube-rl-tracker/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What I Do

Track YouTube video performance to discover patterns in what works. This is "poor man's reinforcement learning" - manually logging outcomes to improve over time.

The RL Loop

1. PUBLISH  -> Upload video with hypothesis (thumbnail style, title hook, topic)
2. WAIT     -> Let it run for 48-72 hours
3. LOG      -> Record in Notion with views, CTR, retention
4. ANALYZE  -> Compare winners vs losers
5. REPEAT   -> Apply learnings to next video

Key Insight from First Data Point

Video 1: "Using AI agents to pay bills and send invoices"

  • 8 views in 1 day
  • Plain talking head thumbnail
  • Generic title

Video 2: "Paying My Contractor Through Claude | AI-Powered Finance"

  • 133 views in 5 days (16x better!)
  • Thumbnail shows: Face + Product UI overlay + Text "I Let AI Pay My Bills"
  • Title has: Specific action + Brand name (Claude) + Category tag

What Made Video 2 Win:

  1. Thumbnail has TEXT overlay - "I Let AI Pay My Bills" creates curiosity
  2. Shows the PRODUCT - UI screenshot proves it's real, not just talk
  3. Face + Context - Person looking at the UI, not just talking
  4. Specific title - "Paying My Contractor" > "pay bills" (concrete vs abstract)
  5. Brand name in title - "Claude" attracts AI-interested audience
  6. Category tag - "AI-Powered Finance" helps discoverability

Hypothesis to Test:

Thumbnails with TEXT + PRODUCT UI + FACE outperform plain talking head thumbnails by 10x+

Database Schema

Core Fields (Outcomes)

Property Type Purpose
Title title Video title
Views number Total views
CTR number Click-through rate (%)
Retention number Average view duration (%)
Days Live number Days since publish
Views/Day formula Views / Days Live
Worked? checkbox Binary gut-check - was this a win?

Read the full file on GitHub · 162 lines

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. 10d ago First seen · 162 lines · 28 tokens per session scan A a6a33644c5aa

Subscribe to this mod's changes

youtube-rl-tracker is a skill published in the GitHub repository different-ai/agent-bank (249 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,447 once invoked, about $0.0001 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens