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-docs/microsite-commerce-storefront/claude-mdgit clone --depth 1 https://github.com/commerce-docs/microsite-commerce-storefrontWrote 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.
[](https://agentmods.dev/instructions/commerce-docs/microsite-commerce-storefront/claude-md)<a href="https://agentmods.dev/instructions/commerce-docs/microsite-commerce-storefront/claude-md"><img src="https://agentmods.dev/badge/instructions/commerce-docs/microsite-commerce-storefront/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00525 | $0.00525 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
microsite-commerce-storefront CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storefront documentation — project memory
Adobe Commerce storefront docs repo (Starlight). Docs live in src/content/docs/**/*.mdx.
The default reader is a beginning developer new to Commerce storefronts, front-end
projects, and Adobe tooling.
Writing docs
When writing or editing any doc, apply these two skills (they load automatically on
.md/.mdx files, or invoke with /<name>):
writing— prose: audience, plain language, voice, tone, sentences, procedures, lists, headings content, grammar, inclusive language, product names.markup— format: Starlight/MDX components, code fences, heading markup, frontmatter, anchor IDs, bold/italic, screenshots.
The two skills cover different domains and do not conflict.
Branch-scoped editorial pass
To scope a writing or markup pass to files changed on the current branch:
BASE=release
git diff --name-only "${BASE}"...HEAD -- '*.md' '*.mdx'
Include uncommitted changes:
git diff --name-only HEAD -- '*.md' '*.mdx'
Union and dedupe both lists. Skip deleted paths. If the list is empty, report that and stop.
Repo conventions
- Use
storefront(notboilerplate) in merchant-facing content. - The boilerplate ships standard drop-ins (cart, checkout, PDP, mini cart, …) already installed and wired up. Write steps only for customization or features beyond the default — not for installing what already exists.
- MDX components: external links use
<Link href="…" text="…" />; notes use<Aside type="note">/<Aside type="tip">. - Never abbreviate
Adobe Commerce as a Cloud ServiceorAdobe Commerce OptimizertoACCS/ACO; spell them out at every mention. These differ fromAdobe Commerce on Cloud(the PaaS offering). - For Starlight and contribution conventions, see
CONTRIBUTING.md.
Migration status
These skills and rules are being migrated from .cursor/ to .claude/. Conversion
conventions and remaining work are tracked in .claude/skills/CONVERSION-NOTES.md.
Commit .claude/ to source control so the team shares the same skills and rules
(unlike .cursor/, which this repo gitignores).
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.
- 4d ago First seen · 55 lines · 525 tokens per session scan A 5430e0f38a98
microsite-commerce-storefront CLAUDE.md is an instructions file published in the GitHub repository commerce-docs/microsite-commerce-storefront (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 525 tokens to every session, about $0.0026 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
ebay-mcp AGENTS.md
Instructions for YosefHayim/ebay-mcp, covering agents.md, what this is, instruction sources, validation commands and module map (src/).
taiwan-ecommerce-toolkit CLAUDE.md
Instructions for Moksa1123/taiwan-ecommerce-toolkit, covering claude.md, project overview, available scripts, test api connectivity and validate invoice data.
rubydex AGENTS.md
AGENTS.md instructions for Shopify/rubydex, covering instructions, project overview, documentation, ruby gem and structure.
GooFish-AIMonitor AGENTS.md
Instructions for tristanwqy/GooFish-AIMonitor, covering agents.md — 给 ai 协作者的工程指南, 黄金规则(先读这条), 验证命令(完成前必跑), 代码地图 and 数据模型要点.
tracepass-mcp-server CLAUDE.md
Claude Code instructions for malinoto/tracepass-mcp-server, covering tracepass-mcp-server, architecture (the one rule everything serves), tool/result conventions to preserve, releasing (three independent channels) and before changing anything.
hw-mcp CLAUDE.md
Instructions for Hertwill/hw-mcp, covering project, constraints, technology stack, executive recommendation and recommended stack.