commerce-agent-bench: Skill for Claude Code

.agents/skills/ecommerce-pr-review/SKILL.md

ecommerce-pr-review is a skill for Claude Code, Codex from harukiseller-droid/commerce-agent-bench. It costs 16 tokens per session (348 once invoked), scanned A, original, MIT.

An evidence-first checklist for reviewing pull requests that change online-store code, such as carts, product pages, templates, integrations, or content.

In plain words
What is it for?
Use it to review commerce facts, checkout and cart behavior, product data, structured data, WooCommerce or Shopify integrations, accessibility, SEO, security, and tests.
Why use it?
It helps catch buyer-facing risks, broken runtime behavior, unsupported claims, and missing checks before a change is approved.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is harukiseller-droid/commerce-agent-bench's own configuration. It tells Claude Code and Codex how to work on commerce-agent-bench itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything commerce-agent-bench configures →

Reuse

Borrowing it

Nothing to install: this file belongs to harukiseller-droid/commerce-agent-bench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/harukiseller-droid/commerce-agent-bench/main/.agents/skills/ecommerce-pr-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/harukiseller-droid/commerce-agent-bench

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 ecommerce-pr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/harukiseller-droid/commerce-agent-bench/ecommerce-pr-review/github.svg)](https://agentmods.dev/skills/harukiseller-droid/commerce-agent-bench/ecommerce-pr-review)
Your own site
<a href="https://agentmods.dev/skills/harukiseller-droid/commerce-agent-bench/ecommerce-pr-review"><img src="https://agentmods.dev/badge/skills/harukiseller-droid/commerce-agent-bench/ecommerce-pr-review/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 ecommerce-pr-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/harukiseller-droid/commerce-agent-bench/ecommerce-pr-review"><img src="https://agentmods.dev/badge/skills/harukiseller-droid/commerce-agent-bench/ecommerce-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 348 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00016 $0.00348
Opus 5 $0.00008 $0.00174
Sonnet 5 $0.00003 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 11d ago against content hash ba7ad3933cdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ecommerce-pr-review 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 11d 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.

.agents/skills/ecommerce-pr-review/SKILL.md · 61 lines

What it actually says

Ecommerce PR Review

Purpose

Review ecommerce pull requests for buyer risk, runtime regressions, unsupported facts, and missing verification.

When to use

Use for any pull request or proposed patch that touches ecommerce code, templates, content, schema, integrations, or agent workflows.

Inputs

  • the pull request diff and base revision;
  • repository protocol and relevant core skills;
  • tests, evals, runtime evidence, and verified merchant data when available.

Required checks

Review in this order:

  1. Commerce fact safety
  2. Runtime regression
  3. Checkout/cart risk
  4. Product data integrity
  5. Schema
  6. WooCommerce/Shopify integration
  7. Accessibility
  8. SEO
  9. Security
  10. Test coverage

Use exact file and line evidence. Check callers and data sources before concluding that a behavior is broken.

Output contract

For each finding, return:

[SEVERITY] rule-id
File: path:line
Evidence: exact source or observed behavior
Risk: practical consequence
Fix: smallest verified fix

Mark unsupported conclusions as UNKNOWN or INFERENCE; never present speculation as a confirmed issue.

Failure conditions

  • Do not approve a commerce claim without traceable evidence.
  • Do not certify runtime, checkout, or platform behavior from static code alone.
  • Do not widen the review into unrelated layout, copy, business logic, or tracking changes.

Verification

Inspect the final diff, run pytest -q and python scripts/run_evals.py, and report remaining unverified runtime or platform risks.

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. 11d ago First seen · 61 lines · 16 tokens per session scan A ba7ad3933cdb

Subscribe to this mod's changes

ecommerce-pr-review is a skill published in the GitHub repository harukiseller-droid/commerce-agent-bench (102 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 348 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.

Related

Other skills, from other repositories

ai-slop

Operational rubric that turns "don't make AI slop" into observable properties, severity levels, evidence requirements, and repair actions for interface design. Use as the reference rubric when building or reviewing marketing sites, product interfaces, dashboards, portfolios, or e-commerce pages, especially alongside…

waybarrios/opencode-power-pack · 61 tokens

woo-guard

Review generated or changed WooCommerce code — extensions, payment and shipping integrations, checkout customizations, and order/product logic — before it ships. Best used reactively after an agent writes, edits, or reviews code touching WooCommerce APIs: wcgetorder, wcgetorders, wcgetproduct, WC() cart or session…

amElnagdy/guard-skills · 216 tokens

vertical-retail

Retail & e-commerce domain knowledge for SMB storefront products (storefront, inventory, pricing, cart-recovery). Codifies the vocabulary (SKU vs variant, reorder point, COGS/margin, ATS, AOV), the non-obvious rules (Shopify owns the storefront — don't fight it head-on; the wedge is multichannel inventory + reorder…

avelikiy/great_cto · 156 tokens

vertical-restaurants

Domain-knowledge primer for the restaurants & hospitality vertical (dine-in, pickup, delivery). Gives architect and pm the vocabulary, non-obvious operating rules, must-model entities, and incumbent landscape so a restaurant-product spec isn't naive about modifiers, 86'd items, aggregator commissions, tip law, and…

avelikiy/great_cto · 88 tokens

magpie-dependency-audit

Read-only dependency vulnerability audit for one repository or a local checkout. Detects the project's dependency manager(s), runs the appropriate audit tool, surfaces patchable findings grouped by severity, and proposes upgrades for maintainer review. Never modifies manifests or lock files and never opens update PRs.

apache/magpie · 66 tokens

magento2-code-review

This skill should be used when the user asks to "review this PR/MR", "review this merge request", "review this module", "audit this module before merge", "review this theme", "audit this theme PR", or wants a "full review before release". Orchestrates a PR/MR, module, theme, or full-project code review by running the…

ddtcorex/maestro-skills · 181 tokens