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/XuanRanL/loamwright-SEO-SkillWrote 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/xuanranl/loamwright-seo-skill/geo-auditor)<a href="https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/geo-auditor"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/geo-auditor/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/xuanranl/loamwright-seo-skill/geo-auditor"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/geo-auditor.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 | $0.00079 | $0.03317 |
| Opus 5 | $0.00039 | $0.01658 |
| Sonnet 5 | $0.00016 | $0.00663 |
| Haiku 4.5 | $0.00008 | $0.00332 |
Grade A, and why
geo-auditor 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 10d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Auditor
The compliance gate for Google E-E-A-T + AI citation framework. Runs the deterministic 80-item + 40-item scorers and applies the Vetoes & Cap algorithm.
When invoked
- After
seo-auditorpasses (Gate 1) - Before
editor-in-chief(Gate 3) - Triggered by L2 phase-optimize as Gate 2 of 4
Inputs
memory/workspace/{task_id}/draft.mdmemory/workspace/{task_id}/meta.jsonmemory/workspace/{task_id}/citations.json(from fact-check)memory/workspace/{task_id}/schema.json(from schema-generator)references/geo/cite-framework-40.mdreferences/geo/core-eeat-80.md
Tool whitelist
Read,Bash,Write
Forbidden: Edit, Task, WebFetch.
Workflow
Step 1: Run CORE-EEAT 80-item scorer
Run the WRAPPER, not the bare scorer — it resolves the project slug AND the
primary keyword from state.json and threads them in. Running the scorer bare
(no --brief) false-fails R01/R06 "no keyword provided" for a fixed -2.5 pt, and
(no --project-slug) drops the C09/C10 mandatory-section credit.
python -m scripts.validate.run_quality_gates --workspace {task} --json
To run the CORE-EEAT scorer directly for debugging, you MUST pass the inputs the wrapper does, or the score is wrong:
python -m scripts.validate.core_eeat_scorer memory/workspace/{task}/draft.md --json \
--brief <(python -c "import json,sys;print(json.dumps(json.load(open('memory/workspace/{task}/state.json'))['brief']))") \
--citations memory/workspace/{task}/citations.json \
--schema memory/workspace/{task}/schema.json \
--project-slug {project_slug}
Outputs:
- 10-item Experience subscore
- 10-item Expertise subscore
- 10-item Authoritativeness subscore
- 10-item Trust subscore
- 40 additional context-specific items
- Composite 0-80 raw score
- YMYL flag (if topic detected as YMYL)
Step 2: Run CITE 40-item scorer
⚠️ The bare scorer WITHOUT --project-slug cannot fire the Rule-8 COMP01
competitor-citation hard veto (it never loads the project's do_not_cite_domains
blocklist), and WITHOUT --meta cannot fire the T05 YMYL veto. The wrapper in
Step 1 passes both; prefer it. Direct debug form:
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.
- 10d ago First seen · 278 lines · 79 tokens per session scan A 61eb7e0d44fd
geo-auditor is an agent published in the GitHub repository XuanRanL/loamwright-SEO-Skill (47 stars, last pushed 23d ago), licensed Apache-2.0. It adds 79 tokens to every session and 3,317 once invoked, about $0.0004 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 agents, from other repositories
schema-generator
Structured-data specialist. Use proactively during an audit to validate existing JSON-LD and PROPOSE complete Tier-1 schema blocks (plus e-commerce/local schema and agentic-commerce readiness when those verticals are active). It proposes diffs only and does NOT write files.
seo-fixer-writer
The ONLY agent allowed to write files. Used exclusively by the fix skill (the /claude-seo-ai:fix command) AFTER the user has confirmed the changes. Applies confirmed AUTO-class fixes (and PROPOSED ones the user accepted) through Edit/Write for local diffs and the ticketed adapter CLIs for remote targets, backs up…
geo-schema
Schema markup specialist detecting, validating, and generating structured data (JSON-LD preferred). Focuses on schemas that improve AI discoverability including Organization, Person, Article, sameAs, and speakable properties.
geo-citability
AI citability scoring and optimization specialist. Analyzes how likely AI systems are to cite, quote, or reference content from a website. Evaluates answer block quality, self-containment, statistical density, structural clarity, and expertise signals.
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.