What is commerce-agent-bench AGENTS.md?

A routing document for coding agents working on an ecommerce project. It lists which review guides to use for different changes and sets rules for checking product facts and code.

Use it before reviewing or changing ecommerce code, especially product pages, WooCommerce templates, schemas, SEO, accessibility, or source code. It also guides preparation of substantial pull-request summaries.

It gives agents a consistent workflow and helps prevent unsupported claims about products, prices, stock, shipping, returns, certifications, or guarantees.

How harukiseller-droid/commerce-agent-bench configures Codex and OpenC

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.md

Clone the repo

git clone --depth 1 https://github.com/harukiseller-droid/commerce-agent-bench

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/harukiseller-droid/commerce-agent-bench/agents-md.svg)](https://agentmods.dev/instructions/harukiseller-droid/commerce-agent-bench/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/harukiseller-droid/commerce-agent-bench/agents-md"><img src="https://agentmods.dev/badge/instructions/harukiseller-droid/commerce-agent-bench/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 493 This file is loaded in full into every session.

When invoked 493 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00493	$0.00493
Opus 5	$0.00246	$0.00246
Sonnet 5	$0.00099	$0.00099
Haiku 4.5	$0.00049	$0.00049

Measured 8d ago against content hash 67e15d46c2df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

commerce-agent-bench AGENTS.md 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 8d 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.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Use this file as the thin routing layer for Codex, Claude Code, Cursor, Gemini CLI, and other coding agents.

Read PROTOCOL.md before reviewing or changing ecommerce code. Load only the relevant core skill from .agents/skills/. Experimental workflows under extras/ are not core routing targets.

Mandatory skill routing

Any ecommerce PR: use .agents/skills/ecommerce-pr-review.
Any product fact change: use .agents/skills/commerce-fact-safety.
Any WooCommerce hook or template change: use .agents/skills/woocommerce-code-review.
Any schema modification: use .agents/skills/schema-validator.
Any source-code modification: use .agents/skills/code-change-verification.
Before completing a substantial PR: use .agents/skills/pr-draft-summary.
For product-page behavior: also use .agents/skills/product-page-audit.
For SEO behavior: also use .agents/skills/technical-seo-audit.
For accessibility behavior: also use .agents/skills/accessibility-audit.

Non-negotiable rules

Never invent product specs, prices, materials, stock, shipping times, returns, ratings, review counts, certifications, or guarantees.
Classify every material claim as FACT, INFERENCE, or UNKNOWN.
For FACT, provide file/path evidence or point to user-supplied verified data.
Prefer runtime platform data over hard-coded commerce values.
Do not change unrelated layout, copy, business logic, or tracking code.
For WooCommerce hooks, check for duplicate registrations before adding callbacks.
For schema, emit only claims visible on-page or present in verified merchant/runtime data.
Do not commit secrets or claim Codex execution without a real Codex run.

Required workflow

Read the task and identify the exact scope.
Inspect the repository and current implementation.
Select and read the mandatory skills.
Collect evidence before proposing or applying a change.
Make the smallest valid change.
Run pytest -q.
Run python scripts/run_evals.py.
Run any relevant benchmark or validator command.
Review the diff, unexpected files, dependencies, generated artifacts, and secrets.
Report verified results, limitations, and remaining risk.

Read the full file on GitHub · 44 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.

8d ago First seen · 44 lines · 493 tokens per session scan A 67e15d46c2df

Subscribe to this mod's changes

commerce-agent-bench AGENTS.md is an instructions file published in the GitHub repository harukiseller-droid/commerce-agent-bench (102 stars, last pushed 26d ago), licensed MIT. It adds 493 tokens to every session, about $0.0025 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.

E-commerce

vibetags com-example-service-OrderService.instructions.md

Instructions for PIsberg/vibetags, covering copilot instructions for orderservice, rules for method calculatetax, rules for method processpayment, rules for method validateorder and context & focus.

PIsberg/vibetags · 553 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

commerce-agent-bench: Instructions file for Codex