- Home
- Skills
- Agents & Orchestration
- Monorepo Dependency Boundary Auditor
Works with the AI Agents you already use
Monorepo Dependency Boundary Auditor
Audit monorepo architecture for circular dependencies, forbidden imports, and package boundary violations.
$14.99
Monorepo Dependency Boundary Auditor
Example session with this skill installed
Audit our pnpm workspace for circular dependencies and layering violations. We use a UI -> App -> Domain -> Core structure. Here are the package.json files and our dependency-cruiser config.
- Read your context and instructions
- Compiled the monorepo dependency boundary
Health Score: 64/100. Verdict: Material boundary erosion. Identified 3 package-level cycles (e.g., @app/auth <> @app/api). Found 12 forbidden imports where 'Core' imports from 'Feature'. Recommended fix: Extract shared interfaces to a new @app/contracts package before tightening Nx tags.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Large monorepos often degrade into a "distributed monolith" where uncontrolled imports, circular dependencies, and version skew break build caching and make releases unpredictable. Manually auditing thousands of internal package boundaries to find forbidden deep imports or layering violations is nearly impossible at scale.
What it does
- Identifies package-level and file-level circular dependencies that block clean builds and deployments.
- Detects forbidden imports, such as domain leakage, layering drift, or production code importing test helpers.
- Audits "shared" and "core" packages for excessive fan-in/fan-out and ownership ambiguity.
- Surfaces version skew across the workspace, including conflicting peer dependencies and duplicate runtime libraries.
- Generates a prioritized remediation sequence and a 100-point boundary-health score.
Frameworks & tools
Supports workspaces using pnpm, Yarn, npm, Nx, and Turborepo. Works with dependency-cruiser, ESLint boundary rules, and TypeScript project references.
Why this beats prompting it yourself
Generic LLM prompts often miss subtle build-graph risks or fail to distinguish between acceptable type-only imports and dangerous runtime cycles. This skill applies a structured rubric to evaluate dependency direction, release coupling, and ownership, ensuring architectural drift is quantified rather than guessed.
Use cases
- Perform a pre-migration audit before moving to a new monorepo manager like Nx or Turbo.
- Identify the root cause of slow CI builds and cache invalidation issues.
- Review a complex Pull Request that introduces new internal package relationships.
- Map ownership and boundaries during a team reorganization or repository split.
Known limitations
Requires access to package manifests, lockfiles, or a dependency graph. It identifies architectural risks but does not perform automated refactoring or file movement.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires access to package manifests, lockfiles, or tree structures. Does not automatically move files or rewrite imports. Analysis of massive repos may require segmenting by domain.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago
Permissions
No special permissions declared or detected