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 agentmods add skills/decebals/claude-code-java/architecture-reviewnpx skills add decebals/claude-code-java --skill architecture-reviewgit clone --depth 1 https://github.com/decebals/claude-code-javaWhat 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 | $0.00051 | $0.02133 |
| Opus 5 | $0.00026 | $0.01066 |
| Sonnet 5 | $0.00010 | $0.00427 |
| Haiku 4.5 | $0.00005 | $0.00213 |
Grade A, and why
architecture-review 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 2d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Review Skill
Analyze project structure at the macro level - packages, modules, layers, and boundaries.
When to Use
- User asks "review the architecture" / "check project structure"
- Evaluating package organization
- Checking dependency direction between layers
- Identifying architectural violations
- Assessing clean/hexagonal architecture compliance
Quick Reference: Architecture Smells
| Smell | Symptom | Impact |
|---|---|---|
| Package-by-layer bloat | service/ with 50+ classes |
Hard to find related code |
| Domain → Infra dependency | Entity imports @Repository |
Core logic tied to framework |
| Circular dependencies | A → B → C → A | Untestable, fragile |
| God package | util/ or common/ growing |
Dump for misplaced code |
| Leaky abstractions | Controller knows SQL | Layer boundaries violated |
Package Organization Strategies
Package-by-Layer (Traditional)
com.example.app/
├── controller/
│ ├── UserController.java
│ ├── OrderController.java
│ └── ProductController.java
├── service/
│ ├── UserService.java
│ ├── OrderService.java
│ └── ProductService.java
├── repository/
│ ├── UserRepository.java
│ ├── OrderRepository.java
│ └── ProductRepository.java
└── model/
├── User.java
├── Order.java
└── Product.java
Pros: Familiar, simple for small projects Cons: Scatters related code, doesn't scale, hard to extract modules
Package-by-Feature (Recommended)
com.example.app/
├── user/
│ ├── UserController.java
│ ├── UserService.java
│ ├── UserRepository.java
│ └── User.java
├── order/
│ ├── OrderController.java
│ ├── OrderService.java
│ ├── OrderRepository.java
│ └── Order.java
└── product/
├── ProductController.java
├── ProductService.java
├── ProductRepository.java
└── Product.java
Pros: Related code together, easy to extract, clear boundaries Cons: May need shared kernel for cross-cutting concerns
Hexagonal/Clean Architecture
What ships with it
1 file 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.
- 2d ago First seen · 330 lines · 51 tokens per session scan A 6d22a092b085
architecture-review is a skill published in the GitHub repository decebals/claude-code-java (722 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 2,133 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
autoimplement
Auto-advance a multi-phase plan: dispatch a subagent per phase, chain /review /pitfall-verification at each boundary, stop on actionable findings. Use for "autoimplement", "run this plan end-to-end", "auto-advance phases".
swiftui-design-consultation
Apple-canon design system for SwiftUI projects: produces DESIGN.md + a Swift Package starter (semantic colors, SF Pro, Liquid Glass, motion, accessibility). Use when starting or refreshing a SwiftUI design system.
ios-native-review
After a PRD/spec/plan for an iOS app, before implementation: validate the artifact against Apple HIG (iOS) via WebFetch citations. Asks "is this iOS-native?" — complements pitfall-verification and quality-review.
office-hours-track-aware
Track-aware wrapper for gstack /office-hours: runs the session, detects native vs web, renders + opens DESIGN.html before the approval gate. Use when starting a new product idea or brainstorming.
pitfall-verification
After any PRD, spec, plan, or code change: verify artifact-specific pitfalls don't apply before declaring done. For ship-worthy changes, auto-chains Codex a third model house + adversarial synthesis.
verify-and-land
Build the checked-out branch, launch that exact app, let the user confirm the fix is really there, then push and offer merge or PR.