mcpbeat Sign in

Architecture Ownership Agent Skill

Determine runtime owner, first-fix layer, and canonical long-term module or package owner in layered codebases. Use when placing code across UI vs platform shell vs runtime orchestration vs domain or application vs shared core vs adapter or integration layers, debugging ownership issues, removing duplicate policy paths, or answering "where should this live?" architecture questions.

2k tokens
context cost
the whole folder, loaded on every use
4
files
instructions only
0
copies elsewhere
how many repositories repackaged it
131
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/instructa/agent-skills --skill architecture-ownership

What comes with it

4 810 bytes besides the instruction
README.md
agents/openai.yaml
references/ownership-matrix.md

The instruction itself

9 sections, as written by the author

Architecture Ownership

Use this skill for repo-specific ownership and placement decisions in layered systems.

Focus on long-term canonical ownership, not only the layer where the current bug appears.

Required Discovery

Before deciding ownership:

  • Read the repo docs that define architecture, boundaries, or responsibilities.
  • Read ADRs or design docs that define runtime flow, request flow, or package boundaries.
  • Inspect the top-level project structure to map the repo's concrete module or package names onto the generic layers in this skill.

When docs are incomplete:

  • infer the current layer model from the codebase
  • state the assumption explicitly
  • keep the recommendation aligned to one canonical owner

Required Output

When answering an ownership or placement question, explicitly separate:

  • Runtime owner
  • First fix owner
  • Canonical long-term owner
  • Competing owners that are wrong
  • Cleanup direction

Do not collapse these into a single answer.

Decision Order

  • Identify the runtime concern:
  • visible UI state
  • platform shell or OS bridge
  • runtime composition or request dispatch
  • canonical domain or application workflow
  • pure shared logic
  • concrete adapter or integration behavior
  • Name the layer where the wrong behavior currently happens.
  • Decide whether that layer is only the First fix owner or also the Canonical long-term owner.
  • If the behavior is reusable product or business policy, move the long-term owner out of the runtime orchestration layer.
  • Remove duplicate policy, fallback logic, or dual paths once the canonical owner is clear.

Layer Map

  • UI layer
  • owns visible UI state, navigation, rendering, presentation-oriented derived state, and view composition
  • Platform shell
  • owns native shell concerns, OS bridges, local device integrations, filesystem or permission bridges, process or session plumbing, and platform-local persistence helpers
  • Runtime orchestration layer
  • owns runtime composition, request dispatch, background coordination, worker management, event publication, and process-level orchestration
  • this is often the First fix owner
  • this is not automatically the Canonical long-term owner
  • Domain or application layer
  • owns canonical product workflow, business rules, reusable application services, and cross-interface behavior
  • Shared core layer
  • owns shared types, enums, validation, normalization, capability logic, and pure logic used across runtimes
  • Adapter or integration layer
  • owns concrete protocol, provider, vendor, transport, or API integration behavior
  • does not own cross-provider or cross-integration product policy

Translate these generic layers into the repo's actual module, package, crate, or service names before making a recommendation.

Hard-Cut Rules

  • Do not leave reusable domain policy in the runtime orchestration layer just because the wrong behavior currently happens there.
  • Do not put UI state, layout state, restore state, or user-facing presentation ownership in the runtime orchestration layer.
  • Do not put platform shell or native integration concerns in the domain or application layer.
  • Do not put cross-provider or cross-vendor product policy in adapter or integration layers.
  • Do not put pure validation, normalization, or capability logic in orchestration code when it can live in shared core or a narrow domain module.

Common Judgments

  • If the question is "who should decide this for all future interfaces?" the answer is usually the domain or application layer, a narrow domain package, or shared core, not the runtime orchestration layer.
  • If the question is "where do I patch this bug first so the product stops doing the wrong thing?" the answer may still be the runtime orchestration layer.
  • If the question is "who owns the wire shape or payload type?" the answer is usually the shared API or core type layer, not the runtime orchestration layer.
  • If the question is "who owns vendor-specific behavior?" the answer is the relevant adapter or integration layer, but only for adapter behavior, not canonical product policy.

Example Pattern

Example: a planning policy bug currently lives in a runtime runner module.

  • Runtime owner: runtime orchestration layer
  • First fix owner: runtime orchestration layer
  • Canonical long-term owner: domain or application layer
  • Type or capability owner: shared core layer
  • Competing owners that are wrong: UI layer, platform shell, adapter or integration layers

Additional Resource

For a reusable classification matrix and example splits, see references/ownership-matrix.md.

Other skills for the same job

different authors, same section of the catalogue
MCP Builder
by anthropics
vendor ×13

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

30k tokens scripts
Changelog Generator
by frostant
×9

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

774 tokens
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
MCP Builder
by JayZeeDesign
×7

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

37k tokens scripts
Vercel React Native Skills
by vercel-labs
vendor ×6

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

39k tokens
Vercel React Best Practices
by ratacat
×5

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

34k tokens
Next Best Practices
by vercel-labs
vendor ×4

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

20k tokens
Using Git Worktrees
by ZhanlinCui
×4

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

1k tokens

How to use it

Copy the folder

Take instructa/architecture-ownership from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.