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 skills add thangchung/agent-engineering-experiment --skill vertical-slice-architecturegit clone --depth 1 https://github.com/thangchung/agent-engineering-experimentWrote 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/skills/thangchung/agent-engineering-experiment/vertical-slice-architecture)<a href="https://agentmods.dev/skills/thangchung/agent-engineering-experiment/vertical-slice-architecture"><img src="https://agentmods.dev/badge/skills/thangchung/agent-engineering-experiment/vertical-slice-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thangchung/agent-engineering-experiment/vertical-slice-architecture"><img src="https://agentmods.dev/badge/skills/thangchung/agent-engineering-experiment/vertical-slice-architecture.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00192 | $0.03242 |
| Opus 5.5 | $0.00077 | $0.01297 |
| Sonnet 5.5 | $0.00038 | $0.00648 |
| Haiku 4.5 | $0.00019 | $0.00324 |
Grade A, and why
vertical-slice-architecture 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vertical Slice Architecture (Clean Architecture, sliced)
This skill encodes the structure of the Hona/VerticalSliceArchitecture template so you can
scaffold components correctly the first time and reason about an unfamiliar repo quickly.
The single most valuable thing here is the wiring map: in this architecture most additions
touch more than one file, and the extra files are not discoverable by reading the file you edit.
Skipping them produces code that compiles and fails at runtime. Read references/wiring.md
before finishing any scaffolding task.
Why this layout exists
Classic Clean Architecture cuts the codebase horizontally — one project per ring, and an
interface at every ring boundary (IGameRepository, IDateTimeProvider, …). The cost is that a
single feature is smeared across four projects, and most of those interfaces have exactly one
implementation forever.
VSA keeps Clean Architecture's dependency rule (dependencies point inward, Domain at the
centre, and nothing in Domain knows about the web or the database) and deletes the
project-per-ring plus interface-per-boundary ceremony. One use case is one file. Coupling is
cut per feature instead of per layer.
Practical consequence: AppDbContext is injected straight into an endpoint. That is deliberate,
not a mistake — do not "fix" it by introducing a repository interface unless the user asks.
Clean Architecture ring → VSA location
| Clean Architecture ring | Lives in | May depend on |
|---|---|---|
| Entities / domain model | Domain/ |
nothing (only BCL + Vogen/Guard attributes) |
| Use cases / application logic | body of HandleAsync in the slice file |
Domain, Common |
| Interface adapters (controller, presenter, DTOs) | same slice file: Configure(), Request, plus Features/{Plural}/Common/{Entity}Response.cs |
Domain, Common |
| Infrastructure / frameworks | Common/EfCore/, Program.cs |
Domain |
Because the use case and its adapter sit in the same file, a slice is read top-to-bottom: DTO, validator, route, logic. That is the property that makes this layout fast to navigate.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 22d ago First seen · 281 lines · 192 tokens per session scan A 2b1bdd7ce63b
vertical-slice-architecture is a skill published in the GitHub repository thangchung/agent-engineering-experiment (27 stars, last pushed 2d ago), licensed MIT. It adds 192 tokens to every session and 3,242 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-25.
Other skills, from other repositories
agui-dotnet-streaming-chat
Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…
azure-maps-search-dotnet
Azure Maps SDK for .NET. Location-based services including geocoding, routing, rendering, geolocation, and weather. Use for address search, directions, map tiles, IP geolocation, and weather data. Triggers: "Azure Maps", "MapsSearchClient", "MapsRoutingClient", "MapsRenderingClient", "geocoding .NET", "route…
azure-mgmt-apicenter-dotnet
Azure API Center SDK for .NET. Centralized API inventory management with governance, versioning, and discovery. Use for creating API services, workspaces, APIs, versions, definitions, environments, deployments, and metadata schemas. Triggers: "API Center", "ApiCenterService", "ApiCenterWorkspace", "ApiCenterApi", "API…
azure-ai-voicelive-dotnet
Azure AI Voice Live SDK for .NET. Build real-time voice AI applications with bidirectional WebSocket communication. Use for voice assistants, conversational AI, real-time speech-to-speech, and voice-enabled chatbots. Triggers: "voice live", "real-time voice", "VoiceLiveClient", "VoiceLiveSession", "voice assistant…
akka-hosting-actor-patterns
Patterns for building entity actors with Akka.Hosting - GenericChildPerEntityParent, message extractors, cluster sharding abstraction, akka-reminders, and ITimeProvider. Supports both local testing and clustered production modes.
omnistudio-callable-apex-generate
Salesforce Industries Common Core (OmniStudio/Vlocity) Apex callable generation and review skill with 120-point scoring. Use when creating, reviewing, or migrating Industries callable Apex implementations. TRIGGER when: user creates or reviews System.Callable classes, migrates VlocityOpenInterface or…