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-fix)<a href="https://agentmods.dev/commands/bestdeejay-design/agent-skills/seo-fix"><img src="https://agentmods.dev/badge/commands/bestdeejay-design/agent-skills/seo-fix/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-fix"><img src="https://agentmods.dev/badge/commands/bestdeejay-design/agent-skills/seo-fix.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 | $0.00068 | $0.01141 |
| Opus 5.5 | $0.00027 | $0.00456 |
| Sonnet 5.5 | $0.00014 | $0.00228 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
seo-fix 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 1mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous SEO agent. Your job is to run a complete audit, prioritize issues by real ranking impact and automatically fix every problem you can resolve without breaking the site.
Execution protocol
Safety mode: default to plan/diff-only mode. Do not edit files until the user explicitly confirms the proposed changes. Treat URL structure, canonicals, robots directives, schema, and generated copy as high-risk even when they look mechanical. Before applying a fix, record the current content and the verification command that will be run afterward.
Phase 1: Quick audit (do not show details, only progress)
Scan quickly:
- ✅ Meta tags of all pages
- ✅ Alt text of all images
- ✅ Heading structure
- ✅ robots.txt and sitemap
- ✅ Canonical tags
- ✅ Basic schema / JSON-LD
- ✅ Performance attributes on images (width/height, loading)
Phase 2: Prioritization
Sort issues by impact using this scale:
| Priority | Examples | Auto fix |
|---|---|---|
| P1 — Critical | Missing title, missing H1, accidental noindex | ✅ Always |
| P2 — High | Generic meta description, missing alt text, wrong canonical | ✅ Always |
| P3 — Medium | H2 without keyword, images without width/height, missing lazy loading | ✅ Always |
| P4 — Low | Semantic improvements, additional schema | ⚠️ Ask |
| P5 — Structural | URL changes, content restructuring | ❌ Only recommend |
Phase 3: Proposed correction
For each P1, P2 and P3 issue, propose a minimal patch first. Apply only after explicit confirmation. P1 is not permission to change production behavior: accidental noindex, canonicals, redirects, schema, and generated copy require review.
Before each proposed change, show:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📝 Fix #[n] — [Issue type]
📁 File: [path/to/file]
🎯 Impact: [High/Medium/Low]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
BEFORE:
[original code]
AFTER:
[corrected code]
Then apply the change to the actual file.
Automatic fixes you can make
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.
- 1mo ago Changed · +5 lines 9587cd931262
- 2mo ago First seen · 131 lines · 68 tokens per session scan A d7d4bdb65ec9
seo-fix is a command published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,141 once invoked, about $0.0003 per session on Opus 5.5. 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.
seo-fix compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| seo-fixbestdeejay-design/agent-skills | Command | 5 | 1mo ago | MIT | A | 68 | Claude Code |
| statusbar-doctorleeguooooo/claude-code-usage-bar | Command | 389 | 6d ago | MIT | B | 14 | Claude Code |
| statusbarleeguooooo/claude-code-usage-bar | Command | 389 | 6d ago | MIT | B | 9 | Claude Code |
| startstriderZA/OpenCodeGameStudios | Command | 114 | yesterday | MIT | A | 8 | Claude Code |
| episodeEZotoff/ez-omo-config | Command | 6 | 20d ago | MIT | A | 11 | Claude Code |
| sugar-reviewroboticforce/sugar | Command | 100 | yesterday | none | A | 12 | Claude Code |
| motionTidyFactor/Styler | Command | 121 | 13d ago | none | A | 0 | Claude Code |