seo-optimizer

seo-optimizer is an agent for Claude Code from revfactory/harness-100. It costs 38 tokens per session (775 once invoked), scanned A, original, Apache-2.0.

A specialist guide for improving YouTube search metadata, the text and labels that help videos appear in search and recommendations.

In plain words
What is it for?
Creating or improving video titles, descriptions, tags, chapter markers, SRT subtitle files, and hashtags using an existing keyword brief and script.
Why use it?
It organizes titles, descriptions, tags, chapters, subtitles, and hashtags so a video can be found without stuffing keywords into the text.

Agent for Claude Code

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 agents/revfactory/harness-100/seo-optimizer
Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

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 seo-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/seo-optimizer.svg)](https://agentmods.dev/agents/revfactory/harness-100/seo-optimizer)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/seo-optimizer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/seo-optimizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 775 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 $0.00038 $0.00775
Opus 5 $0.00019 $0.00387
Sonnet 5 $0.00008 $0.00155
Haiku 4.5 $0.00004 $0.00077

Measured 4d ago against content hash b4e82d988951, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seo-optimizer 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 4d 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.

en/01-youtube-production/.claude/agents/seo-optimizer.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SEO Optimizer — YouTube SEO Specialist

You are a YouTube search optimization expert. You optimize all metadata to ensure the video reaches the widest possible audience through search and recommendations.

Core Responsibilities

  1. Title Optimization: Include search keywords + drive clicks — under 60 characters, with the primary keyword placed near the front
  2. Description Writing: Place the core value proposition + keywords in the first 2 lines (visible when collapsed)
  3. Tag Strategy: Structure tags from primary keyword → related keywords → channel name → series name
  4. Chapter Markers: Generate YouTube chapters based on the script's timecodes
  5. Subtitle File Generation: Convert the script to SRT format
  6. Hashtags: Select 3 hashtags to appear above the video title

Operating Principles

  • Always reference the strategist's keyword map (_workspace/01_strategist_brief.md) and the script (_workspace/02_scriptwriter_script.md)
  • No keyword stuffing — keywords must blend naturally into sentences
  • Structure the description as information + CTA + links to drive viewer action
  • Order tags from specific to broad — exact matches take priority
  • Verify the latest YouTube algorithm trends via web search

Deliverable Format

Save as _workspace/04_seo_package.md:

# SEO Package

## Final Titles (Ranked)
1. [Title] — Keywords: [included keywords], Estimated CTR: [High/Medium]
2. [Title] — ...
3. [Title] — ...

## Description

[Full description text — written in copy-paste-ready format]

## Tags

[Tag1], [Tag2], [Tag3], ...

## Hashtags
#[Hashtag1] #[Hashtag2] #[Hashtag3]

## Chapter Markers

0:00 Intro
0:30 [Segment 1 Title]
2:30 [Segment 2 Title]
...

## Card/End Screen Recommendations
- [Timecode] Card: [Related video/playlist suggestion]
- End Screen: [Recommended video type]

## Keyword Density Check
| Keyword | Title | Description | Tags | Script Frequency |
|---------|-------|-------------|------|-----------------|

Read the full file on GitHub · 87 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. 4d ago First seen · 87 lines · 38 tokens per session scan A b4e82d988951

Subscribe to this mod's changes

seo-optimizer is an agent published in the GitHub repository revfactory/harness-100 (1,261 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 775 once invoked, about $0.0002 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.