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/savant0x/savant-code/coding-javanpx skills add savant0x/savant-code --skill coding-javagit clone --depth 1 https://github.com/savant0x/savant-codeWhat 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 | $0.00021 | $0.00597 |
| Opus 5 | $0.00010 | $0.00298 |
| Sonnet 5 | $0.00004 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
coding-java 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Java Coding Standards
Naming Conventions
| Element | Convention | Example |
|---|---|---|
| Classes | PascalCase | UserProfile, GameState |
| Interfaces | PascalCase | Serializable, Renderable |
| Methods | camelCase | calculateDistance, spawnUnit |
| Variables | camelCase | playerCount, isValid |
| Constants | UPPER_SNAKE_CASE | MAX_PLAYERS, TILE_SIZE |
| Enums | PascalCase (class), UPPER_SNAKE_CASE (values) | TileType.GRASSLAND |
| Packages | lowercase, reversed domain | com.example.gameengine |
| Files | PascalCase.java (match class name) | UserProfile.java |
Patterns
Error Handling
- Use custom exception hierarchy extending
Exception - Catch specific exceptions, never bare
Exception - Use try-with-resources for AutoCloseable
- Log at catch points with context
Concurrency
- Prefer
ExecutorServiceover raw threads - Use
synchronizedorReentrantLockfor shared state - Immutable objects preferred over synchronization
- Use
CompletableFuturefor async composition
Imports
- Group: java → javax → external → internal
- No wildcard imports
- Use IDE auto-import management
File Structure
src/main/java/com/example/
├── Application.java # Entry point
├── config/
│ └── AppConfig.java # Configuration
├── exception/
│ └── AppException.java # Custom exceptions
├── model/
│ └── [Domain].java # Data classes
├── service/
│ └── [Domain]Service.java # Business logic
src/test/java/
└── [Mirror structure]
Anti-Patterns to Flag
- Bare
catch (Exception e) - Mutable static fields
- God classes (>300 lines)
- Deep inheritance hierarchies (>3 levels)
-
nullreturns instead of Optional - Magic numbers (extract to constants)
Quality Overrides
These override the defaults in protocol.config.yaml when Java is the configured language.
| Setting | Default | Java Override | Reason |
|---|---|---|---|
max_file_lines |
300 | 350 | Java boilerplate (imports, generics) adds lines |
max_function_lines |
50 | 40 | Java methods should be shorter due to verbosity |
max_line_length |
100 | 120 | Standard Java convention |
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 · 80 lines · 21 tokens per session scan A 01e5e441b17e
coding-java is a skill published in the GitHub repository savant0x/savant-code (11 stars, last pushed 11d ago), licensed Apache-2.0. It adds 21 tokens to every session and 597 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…