Menu
Use when configuring or running hexcheck in a Go repo for hexagonal architecture boundaries, adapter business-logic warnings, and mock discipline.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when managing per-project backlog folders, feature queues, async agent work items, lifecycle status updates, PR/done/blocked transitions, or status reviews inside an Obsidian vault.
Use when prototyping, authoring agent skills, or asking the agent to zoom out and map unfamiliar code before acting.
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Use when reviewing architecture boundaries, hexagonal architecture, clean architecture layers, dependency direction, trust boundaries, uploads, parsers, redirects, or web security risks.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Use when requesting or receiving code review, dispatching review subagents, running CodeRabbit, deep reviews, simplification/cleanup passes, local branch review, ready-for-PR/finalize intent, finalizer workflow, or preparing work for merge.
| name | hexcheck |
| description | Use when configuring or running hexcheck in a Go repo for hexagonal architecture boundaries, adapter business-logic warnings, and mock discipline. |
Configure .hexcheck.yaml by mapping repo paths to roles. Folder names do not matter; roles do.
Testing status: hexcheck is in a testing phase. If behavior, configuration, diagnostics, or documentation seem off, report it by creating an issue at https://github.com/bnema/hexcheck/issues. Include the repo layout, .hexcheck.yaml, command run, output, and what looked wrong.
Roles:
core: domain/core business logicusecase: application use cases/orchestrationports: interfaces/contractsadapter: infra, persistence, external services, outbound adaptersentrypoint: CLI/HTTP/UI/bootstrapignore: generated code, mocks, vendorMinimal shape:
version: 1
components:
core: { role: core, paths: [internal/domain/**, internal/core/**] }
usecases: { role: usecase, paths: [internal/application/usecase/**, internal/application/usecases/**, internal/usecases/**] }
ports: { role: ports, paths: [internal/application/port/**, internal/domain/repository/**] }
adapters: { role: adapter, paths: [internal/infrastructure/**, internal/adapters/**] }
entrypoints: { role: entrypoint, paths: [cmd/**] }
generated: { role: ignore, paths: ['**/mocks/**', '**/generated/**', '**/*_templ.go', '**/*_gen.go'] }
For repos using boundaries, map by role, e.g. boundaries/in -> entrypoint, boundaries/out -> adapter, boundaries/ports -> ports.
Recommended rules:
rules:
no-adapter-imports-in-core: error
no-infra-imports-in-usecase: error
no-framework-types-in-core: error
no-infra-types-in-ports: error
no-adapter-to-adapter-imports: warn
suspicious-business-logic-in-adapter: warn
no-local-fakes-for-ports: warn
missing-generated-mock-for-port: warn
prefer-generated-mocks: warn
Mock config:
mocking:
generatedMockPaths: [internal/mocks/**, internal/application/mocks/**, internal/application/port/mocks/**]
generatedMockNamePatterns: ['Mock{{Interface}}', '{{Interface}}Mock']
Run:
hexcheck -hexcheck.config .hexcheck.yaml -hexcheck.root . ./...
Agent checklist: read repo architecture docs, map paths to roles, ignore generated/mocks, configure mock paths, run once, tune ruleSettings.*.excludePaths only after inspecting examples.