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 rules/commerce-atoms/agents/30-architecture-boundariesgit clone --depth 1 https://github.com/commerce-atoms/agentsWrote 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/rules/commerce-atoms/agents/30-architecture-boundaries)<a href="https://agentmods.dev/rules/commerce-atoms/agents/30-architecture-boundaries"><img src="https://agentmods.dev/badge/rules/commerce-atoms/agents/30-architecture-boundaries.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 5.1 | $0.00385 | $0.00385 |
| Opus 5 | $0.00192 | $0.00192 |
| Sonnet 5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
30-architecture-boundaries 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 5d 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.
What it actually says
This is a Cursor-specific overlay. Canonical source: rules/core/architecture.md.
Module boundaries — non-negotiable
- Modules NEVER import from other modules.
app/platform/*MUST NOT importapp/modules/*.app/components/*should remain domain-agnostic and SHOULD NOT importapp/modules/*.
Allowed imports from within a module
Relative imports within the same module subtree, plus:
app/components/*(shared UI)app/hooks/*(generic UI hooks only)app/utils/*(generic utilities only)app/platform/*(infrastructure)app/layout/*(app shell — can import from modules for shell integration)@commerce-atoms/*(pure logic packages)
Cross-module reuse ladder
- Duplicate intentionally (< 50 lines).
- Promote to
app/components/**(primitives/,catalog/,commerce/,pagination/). - Promote to
app/hooks/*. - Promote to
app/utils/*. - Extract pure logic to
@commerce-atoms/*. - Create platform utilities.
Forbidden dumping-ground folders
app/lib, app/common, app/shared, app/ui.
Route / view separation
*.route.tsxowns loaders / actions / meta / headers / Storefront API calls.*.view.tsxowns rendering only — no API calls, no sessions, no meta exports.
No barrel files
Never create index.ts exports. Always use explicit imports.
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.
- 5d ago First seen · 49 lines · 385 tokens per session scan A 9a40f366370e
30-architecture-boundaries is a cursor rule published in the GitHub repository commerce-atoms/agents (1 stars, last pushed 4mo ago), licensed MIT. It adds 385 tokens to every session, about $0.0019 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 cursor rules, from other repositories
bootstrap-alwayson
Minimal always-required LLM fixes.
read-xlsx
Reading, writing, diffing, and repairing spreadsheets (.xlsx) for AI agents via the xfa MCP server.
cursorrules
═══════════════════════════════════════════════════════════ SPEC DRIVEN DEVELOPMENT — PROJECT CONSTITUTION Project: Freelance Time Tracker Version: v1.0.
vue
Rules for Vue (2 and 3) single-file components.
RULE
Network troubleshooting — systematic diagnosis and resolution for connectivity, DNS, proxy, SSL, HTTP errors.
55-data-model-versioning
Dataset versioning, model checkpoint management, and training reproducibility rules.