layer-dependency

A rule for keeping high-level project principles separate from tool- and framework-specific implementation details. L1 and L2 refer to the project's upper-level philosophy and decision rules.

In plain words
What is it for?
Use it when editing philosophy or principle files to identify forbidden references and decide whether details belong in lower-level guidelines.
Why use it?
It prevents general guidance from becoming tied to a particular coding tool, framework, or library and helps keep those documents useful over time.

Cursor rule

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 rules/yunbow/ai-dev-os-plugin-cursor/layer-dependency
Clone the repo
git clone --depth 1 https://github.com/yunbow/ai-dev-os-plugin-cursor
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 325 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 $0.00000 $0.00325
Opus 5 $0.00000 $0.00162
Sonnet 5 $0.00000 $0.00065
Haiku 4.5 $0.00000 $0.00032

Measured 2d ago against content hash c051df2ced98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

layer-dependency 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 2d 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.

rules/layer-dependency.mdc · 33 lines

What it actually says

AI Dev OS Layer Dependency Check

When editing L1 (philosophy) or L2 (principles/decision-criteria) files, enforce the dependency rule.

Rules

L1 Philosophy Files

  • MUST NOT contain tool-specific terms: "Claude Code", "Cursor", "Kiro", "Copilot", etc.
  • MUST NOT contain framework-specific terms: "Next.js", "FastAPI", "React", etc.
  • MUST remain abstract and timeless (lifespan: 2-5 years)

L2 Principles / Decision Criteria Files

  • MUST NOT contain framework-specific implementation details
  • MUST NOT reference specific library APIs
  • MAY reference general paradigms (OOP, FP, etc.)
  • MUST remain at the principle level (lifespan: 1-3 years)

When Violations Are Found

Warn the user:

  • Explain which term violates the dependency rule
  • Suggest moving the detail to L3 (guidelines) or L4 (AI frames)
  • Quote the dependency rule: "Upper layers never reference lower layers"

Language

Respond in the same language as the project's .cursorrules file.

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. 2d ago First seen · 33 lines · 0 tokens per session scan A c051df2ced98

Subscribe to this mod's changes

layer-dependency is a cursor rule published in the GitHub repository yunbow/ai-dev-os-plugin-cursor (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 325 tokens. 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.