agentmods.dev

catalogready

catalogready is a skill for Claude Code, Codex from PO-VINCENT/ai-shopping-audit. It costs 90 tokens per session (808 once invoked), scanned A, original, Apache-2.0.

A guide for auditing whether product pages, catalogs, and online stores are understandable and citable by AI shopping assistants. It scores the available product information and drafts fixes based on evidence.

In plain words
What is it for?
Use it to audit product-page HTML, CSV catalogs, or storefronts, review scores and category breakdowns, and prepare the most important listing improvements.
Why use it?
It identifies missing or unclear details that can make products harder for AI systems to find, understand, or recommend.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 5repo 3mo ago A scan 90 tokens original Apache-2.0

Good fit Use it to audit product-page HTML, CSV catalogs, or storefronts, review scores and category breakdowns, and prepare the most important listing improvements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/po-vincent/ai-shopping-audit/catalogready
View source ↗ PO-VINCENT/ai-shopping-audit
Install

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.

Any agent
npx skills add PO-VINCENT/ai-shopping-audit --skill catalogready
Clone the repo
git clone --depth 1 https://github.com/PO-VINCENT/ai-shopping-audit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for catalogready

README.md
[![agentmods](https://agentmods.dev/badge/skills/po-vincent/ai-shopping-audit/catalogready/github.svg)](https://agentmods.dev/skills/po-vincent/ai-shopping-audit/catalogready)
Your own site
<a href="https://agentmods.dev/skills/po-vincent/ai-shopping-audit/catalogready"><img src="https://agentmods.dev/badge/skills/po-vincent/ai-shopping-audit/catalogready/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.

agentmods 80×15 button for catalogready

Your own site · 80×15
<a href="https://agentmods.dev/skills/po-vincent/ai-shopping-audit/catalogready"><img src="https://agentmods.dev/badge/skills/po-vincent/ai-shopping-audit/catalogready.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 808 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.00808
Opus 5.5 $0.00036 $0.00323
Sonnet 5.5 $0.00018 $0.00162
Haiku 4.5 $0.00009 $0.00081

Measured 2mo ago against content hash 7c7dc69d3bac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

catalogready scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. Fetch the page HTML yourself (browser tool, `curl`, or an existing
skills/catalogready/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CatalogReady — AI shopping readiness audit

CatalogReady scores how ready a product page or catalog is for AI shopping assistants and drafts evidence-backed fixes. The core audit is deterministic: no API key, no account, no network beyond fetching the page you are asked to audit.

Choose the entry point

  1. MCP connected (tools named catalogready_* are available): prefer them. Call catalogready_describe once if you need the capability map.
  2. No MCP: use the CLI via uvx --from catalogready-ai catalogready … (or uv run catalogready … inside this repo).

Core workflows

Audit a product page

The audit engine never fetches pages itself — you fetch, it scores.

  1. Fetch the page HTML yourself (browser tool, curl, or an existing file). Note whether it is rendered DOM or raw static HTML; label which one you audited in your summary.
  2. MCP: catalogready_run_product_agent(url, html) — inspects, plans, and validates in one call. For a plain score, catalogready_audit_page_html(url, html). CLI: catalogready agent <url> <html_file> or catalogready page <url> <html_file>.
  3. Report: overall score, per-pillar breakdown, and the top 3–5 fixes with their evidence. Every finding in the result carries evidence — quote it; never add product claims of your own.

Audit a CSV catalog

MCP: catalogready_audit_catalog(catalog_path) (local path). CLI: catalogready catalog <path>.

Discovery bundle (robots/sitemap)

When the user cares about crawler access, also fetch /robots.txt and the sitemap, then catalogready_audit_discovery_bundle(url, html, robots_txt, sitemap_xml) (CLI: catalogready discovery).

AI visibility (is the store actually cited?)

Readiness and observed visibility are separate numbers — never blend them. catalogready_build_visibility_prompt_pack(domain, category, market) builds timestamped observation prompts; after the user records snapshots, catalogready_score_visibility_snapshots(snapshot_path, target_domain) scores them without calling any model.

Read the full file on GitHub · 86 lines

Changes

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.

  1. 2mo ago First seen · 86 lines · 90 tokens per session scan A 7c7dc69d3bac

Subscribe to this mod's changes

catalogready is a skill published in the GitHub repository PO-VINCENT/ai-shopping-audit (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 808 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

E-commerceMarketing and SEOai-agentsai-shoppingchrome-extensiongeomcp
Related

catalogready compared with skills from other repositories

catalogready next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
catalogreadyPO-VINCENT/ai-shopping-auditSkill53mo agoApache-2.0A90Claude Code, Codex
product-feed-optimizeraaron-he-zhu/aaron-marketing-skillsSkill3.1kyesterdayApache-2.0A144Claude Code
domain-hunterReScienceLab/opc-skillsSkill1.9kyesterdayApache-2.0A48Claude Code
ecommerce-seonowork-studio/notfair-pluginSkill4.1k8d agoMITA202Claude Code
paid-ads-amazonnowork-studio/notfair-pluginSkill4.1k8d agoMITA55Claude Code, Codex
seo-content-collection-pageThibaultbm/claude-seo-geoSkill18yesterdayMITA214Claude Code
seo-content-product-pageThibaultbm/claude-seo-geoSkill18yesterdayMITA220Claude Code