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/sumonmselim/agentguard/javanpx skills add SumonMSelim/agentguard --skill javagit clone --depth 1 https://github.com/SumonMSelim/agentguardWhat 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 | $0.00044 | $0.01492 |
| Opus 5 | $0.00022 | $0.00746 |
| Sonnet 5 | $0.00009 | $0.00298 |
| Haiku 4.5 | $0.00004 | $0.00149 |
Grade A, and why
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Java
Design
- Composition over inheritance. Extend only for true is-a relationships
- Immutability by default.
finalfields, no setters unless mutation required - Records for data carriers (16+). No boilerplate POJOs
- Sealed classes for closed type hierarchies (17+). Use exhaustive
switchexpressions over them - Pattern matching
instanceof(16+):if (obj instanceof String s)— no explicit cast - Small interfaces. One concern per interface
- Factory methods or builders over telescoping constructors
- No
nullin public APIs.Optional<T>for absent values. NeverOptionalas field type Objects.requireNonNull(param, "param")at method entry for non-null enforcement
Errors
- Checked exceptions for recoverable conditions callers must handle. Unchecked for programming errors
- Never catch
ExceptionorThrowableexcept at boundaries (HTTP handler, queue consumer) - Log full stack trace. Never swallow exceptions silently
- try-with-resources for all
Closeable. No manualfinallyclose blocks - Catch specific exceptions. Never use exceptions for flow control
Modern Java
varwhere type is obvious from right-hand side. Not to obscure types- Streams for transformation pipelines.
Stream.toList()(16+) overCollectors.toList() List.of(),Map.of(),Set.of()for immutable collections.List.copyOf()for defensive copy- Sequenced collections (21+):
SequencedCollection,getFirst(),getLast()over index hacks switchexpressions over statements. Pattern matching inswitch(21+) with exhaustive coverage- Unnamed patterns and variables (22+, stable 25):
catch (IOException _),case Point(int x, _) - Record patterns (21+):
if (obj instanceof Point(int x, int y)) - Text blocks for multiline strings (SQL, JSON, HTML). No string concat across lines
- Stream gatherers (22+, stable 25):
stream.gather(...)for custom intermediate operations instanceofchecks before casts eliminated — use pattern matching everywhere
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 · 95 lines · 0 tokens per session scan A d11a448d16b9
java is a skill published in the GitHub repository SumonMSelim/agentguard (56 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,492 once invoked, about $0.0002 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
deck-ljg-present
把 outline 1:1 铸成色块大字宣言 deck, 原文不动只做美化。三档主题 black / red / yellow.
data-report
把 CSV/Excel/JSON 数据转成漂亮的可视化报告页.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
deck-presenter-mode
【模板: Presenter Mode Deck】 【意图】怕忘词的演讲者专用 deck, 含逐字稿 notes 与 popup teleprompter。 【布局】.
invoice
标准发票: 寄件/收件 + 明细 + 税 + 总额 + 付款指引.
tcapi
Skill to call Cloud API for Tencent Cloud (腾讯云). Used for cloud automation or resource management. 当用户需要查询、创建、管理腾讯云资源,或执行云 API 自动化操作时触发。优先使用 Octop 自带 venv 中的 tccli,凭证支持全自动 OAuth 登录。.