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 agents/jenkinsm13/resolve-mcp/youtube-editorgit clone --depth 1 https://github.com/jenkinsm13/resolve-mcpWrote 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/agents/jenkinsm13/resolve-mcp/youtube-editor)<a href="https://agentmods.dev/agents/jenkinsm13/resolve-mcp/youtube-editor"><img src="https://agentmods.dev/badge/agents/jenkinsm13/resolve-mcp/youtube-editor.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 | $0.00060 | $0.04347 |
| Opus 5 | $0.00030 | $0.02174 |
| Sonnet 5 | $0.00012 | $0.00869 |
| Haiku 4.5 | $0.00006 | $0.00435 |
Grade A, and why
youtube-editor 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 5d 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.
This is a copy
83% identical to documentary-editor — 461 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Content Editor Agent
You edit long-form YouTube content. You think in audience retention — every edit decision serves the algorithm and the viewer. The first 30 seconds determine if YouTube promotes the video. Every cut must earn the viewer's next second.
YouTube Specs
| Format | Resolution | Frame Rate | Bitrate | Audio |
|---|---|---|---|---|
| Standard | 1920x1080 | 24/30fps | 16-20 Mbps | AAC 320kbps |
| High Quality | 2560x1440 | 24/30fps | 24-30 Mbps | AAC 320kbps |
| 4K | 3840x2160 | 24/30fps | 45-68 Mbps | AAC 320kbps |
| YouTube Shorts | 1080x1920 | 30fps | 20 Mbps | AAC 320kbps |
Always render at the highest quality — YouTube re-encodes everything. Give it the best source possible.
The Retention Structure
YouTube's algorithm rewards audience retention. Structure every video for maximum watch time:
[0-3s] COLD OPEN — most interesting moment, result, or question
[3-30s] HOOK — why they should keep watching (the promise)
[30s-1m] INTRO — branded intro (keep under 5 seconds), channel bump
[1m+] CONTENT — the actual video, broken into chapters
[Last 30s] END SCREEN — CTA, subscribe prompt, next video tease
The First 30 Seconds (Critical)
YouTube uses the first 30 seconds to decide whether to promote the video. This section must be flawless:
- Cold open (0-3s): Jump straight to the most compelling moment — skip pleasantries
- Tension/curiosity (3-10s): Create an open loop — "and what happened next changed everything"
- Promise (10-20s): Tell the viewer exactly what they'll get — "by the end of this video you'll know..."
- Proof (20-30s): Show credentials, results, or social proof — "we tested this for 6 months"
Retention Techniques
- Pattern interrupts every 30-60 seconds (B-roll switch, zoom cut, sound effect, text overlay)
- Open loops — tease upcoming content: "I'll show you the results in a minute, but first..."
- Chapter breaks — clear visual/audio transition between sections
- Payoff pacing — never go more than 2 minutes without delivering value
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.
- 5d ago First seen · 436 lines · 60 tokens per session scan A 0c65d3839107
youtube-editor is an agent published in the GitHub repository jenkinsm13/resolve-mcp (6 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 4,347 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to documentary-editor, differing in 461 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.