Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/commerce-atoms/agentsnpx agentmods add skills/commerce-atoms/agents/validate-architectureWrote 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/skills/commerce-atoms/agents/validate-architecture)<a href="https://agentmods.dev/skills/commerce-atoms/agents/validate-architecture"><img src="https://agentmods.dev/badge/skills/commerce-atoms/agents/validate-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/commerce-atoms/agents/validate-architecture"><img src="https://agentmods.dev/badge/skills/commerce-atoms/agents/validate-architecture.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00045 | $0.01103 |
| Opus 5.5 | $0.00018 | $0.00441 |
| Sonnet 5.5 | $0.00009 | $0.00221 |
| Haiku 4.5 | $0.00005 | $0.00110 |
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 1mo 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
validate-architecture
Replacement for the architecture-validation tool that lived in
mcp-hydrogen-kit. Per ADR 003, the validator logic now lives inside@commerce-atoms/agentsand is exposed as both a Skill and a slash command.
What it does
Walks the target project's app/ directory, parses imports, and reports violations of the architecture rules in AGENTS.md §3 and the canonical sources under rules/core/.
| Code | Severity | Detects |
|---|---|---|
CROSS_MODULE_IMPORT |
error | app/modules/A importing from @modules/B (or relative paths that escape the module). |
REVERSE_IMPORT |
error | app/platform/, app/components/, app/hooks/, or app/utils/ importing from app/modules/*. |
DUMPING_GROUND_FOLDER |
error | Presence of app/lib, app/common, app/shared, or app/ui. |
BARREL_FILE |
error | Any index.ts / index.tsx / index.js / index.mjs under app/. |
REMIX_IMPORT |
error | Imports from @remix-run/* or react-router-dom. |
MISSING_ROUTES_MANIFEST |
error | app/routes.ts is absent. |
FILESYSTEM_ROUTING_LIKELY |
warning | app/routes/ exists without app/routes.ts (suggests filesystem routing). |
MISSING_APP_DIR |
error | The target has no app/ directory at all. |
Invocation
As a slash command
/validate-architecture # validate cwd
/validate-architecture path/to/project # validate a specific path
As an npm CLI
npx @commerce-atoms/agents validate-architecture
npx @commerce-atoms/agents validate-architecture --out path/to/project
npx @commerce-atoms/agents validate-architecture --strict # warnings fail too
npx @commerce-atoms/agents validate-architecture --json # for tool consumption
Programmatically
import {validate, formatReport} from '@commerce-atoms/agents/validate';
const {report, exitCode} = await validate({root: '/path/to/project'});
console.log(formatReport(report));
process.exit(exitCode);
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.
- 1mo ago Changed 8f0a7ff74923
- 2mo ago First seen · 96 lines · 45 tokens per session scan A cbfc2d4432db
validate-architecture is a skill published in the GitHub repository commerce-atoms/agents (1 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,103 once invoked, about $0.0002 per session on Opus 5.5. 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.
validate-architecture compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| validate-architecturecommerce-atoms/agents | Skill | 1 | 1mo ago | MIT | A | 45 | Claude Code, Codex |
| nft-standardswshobson/agents | Skill | 42k | yesterday | MIT | A | 48 | Claude Code |
| code-review-excellencewshobson/agents | Skill | 42k | yesterday | MIT | A | 42 | Claude Code |
| multi-reviewer-patternswshobson/agents | Skill | 42k | yesterday | MIT | A | 49 | Claude Code |
| gentle-ai-collab-perfectGentleman-Programming/gentle-ai | Skill | 8.4k | yesterday | MIT | A | 106 | Claude Code, Codex |
| issue-creationGentleman-Programming/gentle-ai | Skill | 8.4k | yesterday | MIT | A | 30 | Claude Code, Codex |
| skill-creatorGentleman-Programming/gentle-ai | Skill | 8.4k | yesterday | MIT | A | 27 | Claude Code, Codex |