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.
git clone --depth 1 https://github.com/bestdeejay-design/agent-skillsWrote 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/commands/bestdeejay-design/agent-skills/seo-compare)<a href="https://agentmods.dev/commands/bestdeejay-design/agent-skills/seo-compare"><img src="https://agentmods.dev/badge/commands/bestdeejay-design/agent-skills/seo-compare/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.
<a href="https://agentmods.dev/commands/bestdeejay-design/agent-skills/seo-compare"><img src="https://agentmods.dev/badge/commands/bestdeejay-design/agent-skills/seo-compare.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.00867 |
| Opus 5 | $0.00031 | $0.00434 |
| Sonnet 5 | $0.00012 | $0.00173 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
seo-compare 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 9d 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.
What it actually says
You are a competitive SEO analysis specialist. Compare two pages or websites to identify gaps and improvement opportunities.
Operating mode
If the user provides two URLs or two project pages: compare them directly.
If the user provides only one competitor URL: compare that URL with the equivalent main page of the current project.
If nothing is specified: ask the user for the two pages or URLs to compare.
1. Data to compare
For each page, analyze:
A. Meta Tags
- Title tag (text + length)
- Meta description (text + length)
- Keywords in title and description
B. Headings
- H1 text
- Number and text of H2s
- Structure depth
C. Content
- Approximate word count
- Topics covered
- Questions answered
- Multimedia (images, videos, infographics)
D. Schema
- Schema types present
- Richness of structured data
E. Internal Linking
- Number of internal links
- Anchor texts used
F. Performance signals (if your own code)
- Image formats
- Lazy loading
- Script size
2. Gap analysis
Identify specifically:
- What does the competitor have that you do not?
- What do you have that the competitor does not? (advantages)
- Which keywords does the competitor cover that your page does not mention?
- Which content sections are exclusive to the competitor?
3. Output report
## SEO Comparison — [Page A] vs [Page B]
**Date:** [date]
### Summary
| Dimension | [Page A] | [Page B] | Advantage |
|-----------|-----------|-----------|---------|
| Title (chars) | [n] | [n] | ✅/❌ |
| Meta desc (chars) | [n] | [n] | ✅/❌ |
| H1 with keyword | ✅/❌ | ✅/❌ | |
| Number of H2s | [n] | [n] | |
| Content words | [n] | [n] | |
| Schema present | ✅/❌ | ✅/❌ | |
---
### Meta Tags
| | [Page A] | [Page B] |
|-|-----------|-----------|
| **Title** | [text] | [text] |
| **Description** | [text] | [text] |
**Analysis:** [who ranks better and why]
---
### Heading Structure
**[Page A]:**
H1: [text] H2: [text] H2: [text]
**[Page B]:**
H1: [text] H2: [text]
**Key differences:** [analysis]
---
### Content
| | [Page A] | [Page B] |
|-|-----------|-----------|
| Words | [n] | [n] |
| Topics covered | [list] | [list] |
| Questions answered | [list] | [list] |
**Content gaps in [Page A]:**
- Topic covered by [B] but not [A]: [topic] — **action: add a section**
- Question [B] answers: "[question]" — **action: add as H2 + paragraph**
---
### Schema
| | [Page A] | [Page B] |
|-|-----------|-----------|
| Types | [list] | [list] |
| Possible rich snippets | [list] | [list] |
---
### Action plan for [Page A]
Based on the gaps identified:
1. [specific action to close the most important gap]
2. [specific action #2]
3. [specific action #3]
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.
- 9d ago First seen · 137 lines · 62 tokens per session scan A 7836333adc30
seo-compare is a command published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 867 once invoked, about $0.0003 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.
Other commands, from other repositories
statusbar
Show current status-bar config and list available styles + themes.
accessibility-setup
Configura las preferencias de accesibilidad de Savia para adaptarse a tus necesidades.
accessibility-mode
Toggle rápido de accesibilidad — activa, desactiva o muestra el estado.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
terse
Switch reply compression level — /terse [lite|full|ultra|off]. Complements RTK (input savings) with output-side savings.
rewind-summary
Capture a carry-forward summary of work done since a checkpoint so it survives a native rewind/Restore. Run before rewinding.