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.
npx agentmods add instructions/commerce-atoms/agents/agents-mdgit clone --depth 1 https://github.com/commerce-atoms/agentsWhat 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 | $0.00666 | $0.00666 |
| Opus 5 | $0.00333 | $0.00333 |
| Sonnet 5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
agents 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 yesterday.
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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — @commerce-atoms/agents repo (kit authoring)
If an AI agent is reading this file, you are working on the @commerce-atoms/agents npm package itself, not a Hydrogen storefront. Read CONTRIBUTING.md before doing anything else.
What this repo is
The @commerce-atoms/agents package distributes a kit of AI rules, skills, commands, prompts, and personas to consumer storefronts. The shipped product lives under kit/ and is governed by kit/AGENTS.md. This repo's source code lives under src/ and bin/, and is governed by this file plus CONTRIBUTING.md.
The audiences and rules differ:
| You're working in… | Read | Don't apply |
|---|---|---|
src/, bin/, package.json, workflows |
This file + CONTRIBUTING.md |
kit/AGENTS.md (those rules are about Hydrogen apps) |
kit/ (rules, skills, commands, prompts, personas, reference, docs) |
kit/AGENTS.md + kit/reference/conventions.md |
none |
Doctrine for kit authoring
- The root is config;
kit/is product. Don't move kit-authoring concerns intokit/, and don't move storefront concerns into the root. If the rule wouldn't apply to a consumer, it doesn't ship. - Strict TypeScript across
src/andbin/. No.js/.mjssource. Noany.npm run verifymust be green before push. - Every shipped artefact lives in
kit/INDEX.json. Missing or broken paths failnpm run lint:jsonin CI. - Synced files have their relative links rewritten to absolute GitHub URLs at sync time. Don't pre-rewrite links in source files; let
src/internal/rewrite-links.tsdo it. - Releases go through
git tag+publish.yml(OIDC Trusted Publishing). Nevernpm publishfrom a workstation against this package — the CI path is the only audited surface.
Quick reference
- Architecture, primitives, conventions for the kit:
kit/AGENTS.md. - How to add to the kit:
CONTRIBUTING.md→ "Kit content". - ADRs:
kit/docs/decisions/. - CLI source:
src/sync.ts,src/init.ts,src/validate.ts. - CLI entrypoint:
bin/sync.ts. - Release flow:
CONTRIBUTING.md→ "Releasing".
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.
- yesterday First seen · 32 lines · 666 tokens per session scan A 4a4f79a75125
agents AGENTS.md is an instructions file published in the GitHub repository commerce-atoms/agents (1 stars, last pushed 4mo ago), licensed MIT. It adds 666 tokens to every session, about $0.0033 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.
Other instructions, from other repositories
syncai copilot-instructions.md
Instructions for dmtrkzntsv/syncai, covering claude.md, build & run, architecture, lifecycle and identify is the routing decision.
wordpress-claude-stack CLAUDE.md
Instructions for mvtandas/wordpress-claude-stack, covering wordpress project — claude code instructions, stack, code style, php and theme development.
PixelPilot uiux-forms.instructions.md
Multi-step forms, validation, autocomplete, and submission patterns.
PixelPilot uiux-graphql.instructions.md
GraphQL API integration including Apollo Client, URQL, code generation, caching strategies, and 2026 GraphQL-first APIs.
wordpress-claude-stack copilot-instructions.md
Instructions for mvtandas/wordpress-claude-stack, covering copilot instructions — wordpress project, framework, generate code that and never generate.
syncai AGENTS.md
Instructions for dmtrkzntsv/syncai, covering claude.md, build & run, architecture, lifecycle and identify is the routing decision.