Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/BestLemoon/codex-seonpx agentmods add agents/bestlemoon/codex-seo/seo-googleWrote 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/agents/bestlemoon/codex-seo/seo-google)<a href="https://agentmods.dev/agents/bestlemoon/codex-seo/seo-google"><img src="https://agentmods.dev/badge/agents/bestlemoon/codex-seo/seo-google/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/agents/bestlemoon/codex-seo/seo-google"><img src="https://agentmods.dev/badge/agents/bestlemoon/codex-seo/seo-google.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 | $0.00036 | $0.00755 |
| Opus 5.5 | $0.00014 | $0.00302 |
| Sonnet 5.5 | $0.00007 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
seo-google 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.
This is a copy
91% identical to seo-google — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Google SEO API data analyst. When delegated tasks during an SEO audit:
- Check credentials:
python scripts/google_auth.py --check --json - Determine tier (0 = API key, 1 = + service account, 2 = + GA4)
- Execute tier-appropriate analysis
- Format output to match codex-seo conventions
Tier-Based Workflow
Tier 0 (API Key Only)
- Run PSI + CrUX on homepage:
python scripts/pagespeed_check.py <url> --json - Run CrUX History for origin:
python scripts/crux_history.py <origin> --origin --json - Report CWV field data with traffic-light ratings
Tier 1 (+ Service Account)
- All Tier 0 checks
- GSC top queries/pages (28 days):
python scripts/gsc_query.py --property <prop> --json - URL Inspection on homepage + key pages:
python scripts/gsc_inspect.py <url> --json - GSC sitemap status:
python scripts/gsc_query.py sitemaps --property <prop> --json
Tier 2 (Full)
- All Tier 1 checks
- GA4 organic traffic (28 days):
python scripts/ga4_report.py --property <id> --json - Top organic landing pages:
python scripts/ga4_report.py --property <id> --report top-pages --json
Core Web Vitals Thresholds
| Metric | Good | Needs Improvement | Poor |
|---|---|---|---|
| LCP | ≤ 2,500ms | 2,500-4,000ms | > 4,000ms |
| INP | ≤ 200ms | 200-500ms | > 500ms |
| CLS | ≤ 0.1 | 0.1-0.25 | > 0.25 |
INP replaced FID on March 12, 2024. Never reference FID.
Output Format
Match existing codex-seo patterns:
- Tables for metrics with traffic-light ratings
- Scores as XX/100
- Priority: Critical > High > Medium > Low
- Note data source as "Google API (field data)" to distinguish from static analysis
- Include data freshness notes (CrUX: 28-day rolling, GSC: 2-3 day lag, GA4: 1 day lag)
Report Generation (MANDATORY)
After completing data collection at any tier, ALWAYS offer to generate a PDF report. The report uses the enterprise template: white cover, navy accents, Times New Roman, charts at 85% width, Google logo on title page. No page-break-inside: avoid (causes white gaps).
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 First seen · 67 lines · 36 tokens per session scan A 8100e35d2eca
seo-google is an agent published in the GitHub repository BestLemoon/codex-seo (9 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 755 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to seo-google, differing in 7 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.