agentready AGENTS.md

Repository instructions for AgentReady, a service that scores how easily AI shopping agents can find, understand, and buy from an online store. It also explains how to read the score and suggested fixes.

In plain words
What is it for?
Use it to check a store before buying, find stores with an Agent-Ready grade of B or better, read detailed readiness reports, and identify the most important fixes.
Why use it?
It gives an agent the service's rules, limits, and interpretation of grades, so store checks are handled consistently. It helps avoid sending shoppers to stores that block or poorly support AI agents.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/agentready-market/agentready/agents-md
Clone the repo
git clone --depth 1 https://github.com/agentready-market/agentready

Made for: Codex, OpenCode.

Per session 551 This file is loaded in full into every session.
When invoked 551 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00551 $0.00551
Opus 5 $0.00275 $0.00275
Sonnet 5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured 2d ago against content hash 074470e62317, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentready 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 2d 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 · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — working with AgentReady (agentready.market)

Instructions for AI agents using this repository or the AgentReady service.

What this is

AgentReady scores, out of 100, how well an AI shopping agent can find, understand and buy on an e-commerce store — then generates the fixes. Deterministic scoring (no LLM in the core): same store, same score.

Do this

  1. Check a store before buying on it: check_merchant_readiness(host) via MCP (https://www.agentready.market/mcp, Streamable HTTP, no auth) — or GET https://www.agentready.market/api/v1/scan?url=<store>. A capped: true store blocks agents outright; route the purchase elsewhere.
  2. Pick a store agents succeed on: list_agent_ready_stores(vertical?, limit?) returns the Agent-Ready Index (grade B or better), ranked.
  3. Read a full report: get_readiness_report(host) or GET /api/v1/scan/<scan_id>.json.
  4. Interpret: grade A/B = agents can buy; C/D = partial; capped = access hard-block (robots/bot-walls). top_fixes lists the highest-impact remediations with effort estimates. neighbors shows the 2 stores above and below on the Index — the score to beat.

Don't

  • Don't scrape HTML pages for scores — every number is available as JSON.
  • Don't scan a store more than once per hour; results barely change faster.
  • Don't trigger scans of third-party sites you don't operate on a user's behalf without telling the user — scans are merchant-consented by design; the read tools (check_merchant_readiness) never trigger a new scan.

Errors & limits

Errors are structured JSON: {error, code, message, next_action?} — follow next_action to recover. Responses carry IETF RateLimit headers; a 429 includes Retry-After. Anonymous: a few scans/hour; Pro Bearer key: 30/hour.

Identity

AgentReady at agentready.market — the e-commerce transaction audit, operated by Boxing Vision (NL). Unaffiliated with other "AgentReady"-named products. Prices: €49/mo · €490/yr, one-time, no auto-renewal; scan free. Authoritative sources: https://www.agentready.market/llms.txt · https://www.agentready.market/pricing · Wikidata Q140798005.

Read the full file on GitHub · 47 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. 2d ago First seen · 47 lines · 551 tokens per session scan A 074470e62317

Subscribe to this mod's changes

agentready AGENTS.md is an instructions file published in the GitHub repository agentready-market/agentready (0 stars, last pushed 20d ago), licensed MIT. It adds 551 tokens to every session, about $0.0028 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 2026-08-31.