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 commands/mverab/egeoagents/geo-optimizegit clone --depth 1 https://github.com/mverab/eGEOagentsWrote 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/mverab/egeoagents/geo-optimize)<a href="https://agentmods.dev/commands/mverab/egeoagents/geo-optimize"><img src="https://agentmods.dev/badge/commands/mverab/egeoagents/geo-optimize.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 | $0.00015 | $0.00409 |
| Opus 5 | $0.00008 | $0.00204 |
| Sonnet 5 | $0.00003 | $0.00082 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
geo:optimize 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.
What it actually says
/geo:optimize Command
Quick optimization of local content files.
Workflow
- Validate MCPs - Run
validation-doctor; if missing, provide setup snippets - Frontmatter Extraction - If the input file contains frontmatter (YAML block between
---or TOML block between+++), extract and preserve this block completely. Do not pass the frontmatter to the analyzer or rewriter agents. Only pass the content body. - Analyze - Read and score the content body (source of truth)
- Rewrite - Apply GEO optimization to the content body based on analyzer output
- Schema - Generate appropriate markup based on analyzer output
- Reassemble & Export - Output the optimized version to the
geo-output/optimized/directory:- markdown: Reassemble the file by prepending the original, unmodified frontmatter to the optimized content body. Save as
[name].md. - html: Convert the optimized content body to HTML (preserving all headers, tables, lists, and formatting). Insert the original frontmatter properties into appropriate HTML metadata tags (
<meta>or structured header) inside a clean, modern HTML document template. Save as[name].html.
- markdown: Reassemble the file by prepending the original, unmodified frontmatter to the optimized content body. Save as
Output
- Optimized content (with frontmatter preserved or converted to HTML metadata)
- Schema markup if applicable
- Change summary with impact estimates
Example Usage
/geo:optimize ./content/homepage.md
/geo:optimize ./content/homepage.md html
/geo:optimize ./blog/new-post.md markdown
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.
- 4d ago First seen · 41 lines · 15 tokens per session scan A e435aa59fd4a
geo:optimize is a command published in the GitHub repository mverab/eGEOagents (172 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 409 once invoked, about $0.0001 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.
Other commands, from other repositories
rank-compete
Competitive X-Ray. Compare your site's SEO signals, tech stack, content depth, and conversion patterns against any competitor URL.
rank-perf
Performance and mobile-first indexing audit from HTML — no Chrome needed.
rank-citability
Score how likely AI search engines are to cite your content.
rank-security
Security headers and HTTPS compliance audit for SEO.
rank
SEO/GEO/AEO audit, analysis, and optimization. The most comprehensive search toolkit for Claude Code.
rank-audit
Full SEO/GEO/AEO audit with auto-fix. Scans, reports, fixes, and verifies.