validate-architecture

validate-architecture is a command for coding agents from commerce-atoms/agents. It costs 26 tokens per session (366 once invoked), scanned A, original, MIT.

A command that runs the architecture checks for the current Hydrogen storefront project or a specified path. It reports whether the project passes, has warnings, or fails the defined structure rules.

In plain words
What is it for?
Use it after adding modules, changing route manifests, or promoting shared code, and before marking those structural changes complete.
Why use it?
It turns the architecture review into a repeatable check and shows the file paths and remedies when the structure is invalid.

Command

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 commands/commerce-atoms/agents/validate-architecture
Clone the repo
git clone --depth 1 https://github.com/commerce-atoms/agents

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 validate-architecture

README.md
[![agentmods](https://agentmods.dev/badge/commands/commerce-atoms/agents/validate-architecture.svg)](https://agentmods.dev/commands/commerce-atoms/agents/validate-architecture)
Your own site
<a href="https://agentmods.dev/commands/commerce-atoms/agents/validate-architecture"><img src="https://agentmods.dev/badge/commands/commerce-atoms/agents/validate-architecture.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 366 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00026 $0.00366
Opus 5 $0.00013 $0.00183
Sonnet 5 $0.00005 $0.00073
Haiku 4.5 $0.00003 $0.00037

Measured 3d ago against content hash b66c83fcc244, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate-architecture 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 3d 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.

kit/commands/validate-architecture.md · 39 lines

What it actually says

/validate-architecture

Run the architecture validators against a Hydrogen storefront project.

Workflow

  1. Resolve the target directory:

    • If the user supplied a path, use it.
    • Otherwise, use the current working directory.
  2. Invoke the CLI:

    npx @commerce-atoms/agents validate-architecture --out <path>
    
  3. Read the human-readable output. If exit code is non-zero, summarise violations grouped by code for the user.

  4. After structural changes (new module, manifest edits, shared-folder promotions), paste the summary into the PR or notes before marking work complete.

Output expectations

  • PASS — exit 0, no further action needed.
  • WARN — exit 0 (unless --strict), but surface the warnings to the user with their remedies.
  • FAIL — exit 1, list every error with file path and remedy. Do not mark the work complete until errors are addressed or explicitly accepted.

See also

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. 3d ago First seen · 39 lines · 26 tokens per session scan A b66c83fcc244

Subscribe to this mod's changes

validate-architecture is a command published in the GitHub repository commerce-atoms/agents (1 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 366 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 2026-08-31.