Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadAppGang/magus/plugin install devWrote 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/madappgang/magus/architecture)<a href="https://agentmods.dev/skills/madappgang/magus/architecture"><img src="https://agentmods.dev/badge/skills/madappgang/magus/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/madappgang/magus/architecture"><img src="https://agentmods.dev/badge/skills/madappgang/magus/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 | $0.00053 | $0.02081 |
| Opus 5.5 | $0.00021 | $0.00832 |
| Sonnet 5.5 | $0.00011 | $0.00416 |
| Haiku 4.5 | $0.00005 | $0.00208 |
Grade A, and why
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 1mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture index
You are holding the index, not the content. Its job is to name the one or two files that answer the question in front of you, so a question about Observer does not drag in Visitor, Memento, and eight others.
Read only what the task calls for. The full tree is ~30 files. Two is normal. Five means the task is really several tasks and should be split.
Paths resolve against this skill's own directory — the tree this file was loaded from.
Step 1: pick the altitude
The single most common mistake is answering at the wrong altitude. Both tiers use the word "pattern" and they are not the same thing.
| The question is about | Altitude | Go to |
|---|---|---|
| how a whole system or service is shaped: what depends on what, where the boundaries sit, how services talk | Style | references/styles/ — Step 2 |
| how a handful of classes collaborate: how to construct this, how to vary that behaviour, how to decouple these two | Design pattern | references/ category leaf — Step 3 |
| changing existing code without changing what it does — it is hard to edit, hard to test, or the same edit keeps recurring | Refactoring | references/refactoring.md — Step 4 |
| recording a decision so the trade-off survives the people who made it | ADR | references/adr.md |
| which of the two you even need | either | references/selection.md first |
A test that resolves it fast: if the answer changes your directory layout or your deploy unit, it is a style. If it changes one module's class graph, it is a design pattern. "Should the database be swappable" is a style question. "How do I swap the hashing algorithm at runtime" is Strategy.
Step 2: architectural styles
Read references/styles/<file>.md. These are mutually comparable, so read at most two and
compare them; reading all seven is a survey, not a decision.
| Read | When the pressure is |
|---|---|
references/styles/layered.md |
default separation of concerns; the team wants structure and has no exotic constraint |
references/styles/hexagonal.md |
the domain must not know about the database, HTTP, or the queue; you want to test business logic with no infrastructure running |
references/styles/clean.md |
hexagonal plus an opinionated inner ring of entities and use cases; larger teams wanting one prescribed layout |
references/styles/modular-monolith.md |
you want service-shaped boundaries without service-shaped operations; the usual correct answer before microservices |
references/styles/microservices.md |
independent deploy and independent scaling are worth a distributed system's cost; you can already name the boundaries |
references/styles/event-driven.md |
producers must not know consumers; work is asynchronous; you need to add reactions without editing the producer |
references/styles/cqrs-event-sourcing.md |
reads and writes have genuinely different shapes or loads; you need history and audit as a first-class fact |
What ships with it
50 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.
- assets/patterns/middleware.ts 3.7 KB runs code
- assets/patterns/patterns.test.ts 9.2 KB runs code
- assets/patterns/state-machine.ts 2.4 KB runs code
- assets/patterns/strategy.ts 2.5 KB runs code
- bun.lock 1.2 KB
- check-index.sh 11 KB runs code
- package.json 420 B
- references/adr.md 25 KB
- references/behavioral.md 5.9 KB
- references/creational.md 4.0 KB
- references/patterns/abstract-factory.md 3.6 KB
- references/patterns/adapter.md 3.7 KB
- references/patterns/bridge.md 3.7 KB
- references/patterns/builder.md 3.7 KB
- references/patterns/chain-of-responsibility.md 4.3 KB
- references/patterns/command.md 3.6 KB
- references/patterns/composite.md 3.8 KB
- references/patterns/decorator.md 5.5 KB
- references/patterns/facade.md 3.3 KB
- references/patterns/factory-method.md 3.4 KB
- references/patterns/flyweight.md 3.7 KB
- references/patterns/iterator.md 3.5 KB
- references/patterns/mediator.md 4.6 KB
- references/patterns/memento.md 5.1 KB
- references/patterns/observer.md 4.2 KB
- references/patterns/prototype.md 3.4 KB
- references/patterns/proxy.md 3.7 KB
- references/patterns/singleton.md 4.2 KB
- references/patterns/state.md 4.1 KB
- references/patterns/strategy.md 4.0 KB
- references/patterns/template-method.md 4.4 KB
- references/patterns/visitor.md 4.1 KB
- references/real-world-examples.md 27 KB
- references/refactoring.md 18 KB
- references/refactoring/techniques/composing-methods.md 36 KB
- references/refactoring/techniques/dealing-with-generalization.md 64 KB
- references/refactoring/techniques/moving-features.md 86 KB
- references/refactoring/techniques/organizing-data.md 94 KB
- references/refactoring/techniques/simplifying-conditionals.md 89 KB
- references/refactoring/techniques/simplifying-method-calls.md 128 KB
- references/selection.md 6.9 KB
- references/structural.md 4.8 KB
- references/styles/clean.md 5.4 KB
- references/styles/cqrs-event-sourcing.md 6.4 KB
- references/styles/event-driven.md 5.9 KB
- references/styles/hexagonal.md 5.4 KB
- references/styles/layered.md 5.0 KB
- references/styles/microservices.md 5.3 KB
- references/styles/modular-monolith.md 5.4 KB
- tsconfig.json 352 B
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.
- 1mo ago First seen · 142 lines · 53 tokens per session scan A 270254ed2d01
architecture is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 2,081 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
dev-runtime
How the Node side of a dev stack runs without haven, and the backend host: pnpm dev (UI built once, backend reloading), pnpm dev:hmr (adds the Vite ui lane), tools/dev-runtime (api + worker in one Node process), backend reload on a file change, the debounce (quiet window + max wait), ports derived from PORT. Use when…
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…