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/audit-ecommerce)<a href="https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/audit-ecommerce"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/audit-ecommerce/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/audit-ecommerce"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/audit-ecommerce.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 | $0.00035 | $0.01053 |
| Opus 5 | $0.00017 | $0.00526 |
| Sonnet 5 | $0.00007 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
audit-ecommerce 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit E-commerce Agent
Spawn Condition
config.json :: business_type == "ecommerce", OR crawl results contain Product schema or product URL patterns (/product/, /shop/, /p/).
Inputs
{audit_dir}/crawl-results.json— product pages with HTML, schema, links{audit_dir}/config.json— domain, product URL patterns, category structure
Read references/audit/schema-types.md before analysis.
Scripts
python -m scripts.audit.parse_html {html_path} --url {page_url} --json— the file is positional; output includes aschemaarray with every JSON-LD block (there are no--extract-*flags, and pricing is not extracted — read visible prices from the HTML yourself)python -m scripts.validate.schema_validator {schema_json_file} --json— deep validation of a JSON-LD payload (or list of payloads) saved to a file; the file argument is positional and there is no--typeflag (it detects types itself)
10 Checks
1. Product Schema — Every product page needs Product with: name, image, description, sku, brand.name, offers. CRITICAL if absent; HIGH if offers missing; MEDIUM if recommended fields missing.
2. Offer Schema — Each offers must have: price (numeric, matches visible), priceCurrency (ISO 4217), availability (InStock/OutOfStock/PreOrder/BackOrder/Discontinued), url. HIGH if price or availability missing.
3. AggregateRating — If reviews visible on page: ratingValue + reviewCount must exist in schema and match displayed stars. HIGH if reviews visible but no schema.
4. Variant Handling — Products with size/color variants: parent should use ProductGroup or Product+hasVariant. Each variant needs own Offer+sku. Single canonical URL preferred. MEDIUM if variants create duplicate title/description.
5. Breadcrumbs — Visible trail Home > Category > Subcategory > Product with matching BreadcrumbList schema (ListItem with name + item URL). HIGH if schema absent on product pages.
6. Internal Linking — Category->product links, product->related (3-6), product->category via breadcrumb, cross-sell/upsell sections. Target 5-10 internal links per product page. MEDIUM if avg < 3.
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 · 61 lines · 35 tokens per session scan A 1fe8b6c48b8a
audit-ecommerce is an agent published in the GitHub repository XuanRanL/loamwright-SEO-Skill (47 stars, last pushed 23d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,053 once invoked, about $0.0002 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
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…
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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.