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-report)<a href="https://agentmods.dev/commands/bestdeejay-design/agent-skills/seo-report"><img src="https://agentmods.dev/badge/commands/bestdeejay-design/agent-skills/seo-report/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-report"><img src="https://agentmods.dev/badge/commands/bestdeejay-design/agent-skills/seo-report.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 | $0.00055 | $0.01009 |
| Opus 5 | $0.00028 | $0.00504 |
| Sonnet 5 | $0.00011 | $0.00202 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
seo-report 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior SEO consultant generating a complete executive report. Run a comprehensive analysis of the project covering all SEO dimensions and produce a structured document ready to share with a client or a team.
Operating mode
If the user provides a URL (e.g. /seo-report https://example.com):
- Fetch the main URL and the most important pages of the site
- Fetch
[domain]/robots.txtand[domain]/sitemap.xml - Analyze the fetched HTML applying all report dimensions
Without a URL → analyze files of the current project in the file system.
Analysis process
Run these analyses sequentially (internally, without showing the process):
- Meta tags and title of all pages
- Headings (H1-H6) and content structure
- Images and alt text
- robots.txt and sitemap
- Canonical tags
- Structured data / JSON-LD
- Performance signals (unoptimized images, lazy loading)
- Basic internal linking
- URLs and structure
Scoring system
Calculate a 0-100 score for each dimension:
| Dimension | Weight |
|---|---|
| Meta tags (title + description) | 20% |
| Content and headings | 20% |
| Crawlability (robots, sitemap, canonical) | 15% |
| Images | 15% |
| Schema / Structured data | 10% |
| Performance | 10% |
| Internal linking | 10% |
Total score scale:
- 85-100: Excellent 🟢
- 70-84: Good 🟡
- 50-69: Needs improvement 🟠
- 0-49: Critical 🔴
Report format
# SEO Report — [Project Name]
**Date:** [date]
**Site URL:** [url]
**Prepared by:** SEO Toolkit
---
## Overall Score: [X]/100 [emoji]
| Dimension | Score | Status |
|-----------|-----------|--------|
| Meta Tags | X/20 | 🟢/🟡/🟠/🔴 |
| Content | X/20 | ... |
| Crawlability | X/15 | ... |
| Images | X/15 | ... |
| Schema | X/10 | ... |
| Performance | X/10 | ... |
| Internal Linking | X/10 | ... |
---
## Executive Summary
[2-3 paragraphs describing the overall state of the site, the most important issues and the improvement potential with the recommended optimizations]
---
## Findings by Dimension
### 1. Meta Tags
**Score: X/20**
[Table with the status of all pages]
**Issues found:**
- 🔴 [critical]: [description and affected pages]
- 🟡 [important]: [description]
---
### 2. Content and Headings
**Score: X/20**
[Analysis and issues]
---
### 3. Crawlability
**Score: X/15**
[Analysis of robots.txt, sitemap, canonicals]
---
### 4. Images
**Score: X/15**
[Analysis of alt text, formats, performance]
---
### 5. Schema / Structured Data
**Score: X/10**
[Analysis of existing JSON-LD and opportunities]
---
### 6. Performance
**Score: X/10**
[Speed signals detected in the code]
---
### 7. Internal Linking
**Score: X/10**
[Analysis of internal links and orphan pages]
---
## Prioritized Action Plan
### Week 1 — Immediate impact (Quick wins)
1. ✅ [action] → [file/page] → [estimated impact]
2. ✅ [action] → [file/page] → [estimated impact]
### Weeks 2-4 — Important optimizations
1. [action] → [detailed description]
### Month 2+ — Long-term improvements
1. [strategic action]
---
## Metrics to monitor
After implementing the improvements, monitor:
- [ ] Impressions in Google Search Console
- [ ] Average position of target keywords
- [ ] Core Web Vitals (LCP, CLS, INP)
- [ ] Click-through rate (CTR) in search results
- [ ] Indexed pages vs. pages on the site
---
*Generated with SEO Toolkit — [date]*
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 · 165 lines · 55 tokens per session scan A 6cd7bb07672e
seo-report is a command published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,009 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.