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/showmethecold/effective-java-skill/apply-effective-javanpx skills add showmethecold/effective-java-skill --skill apply-effective-javagit clone --depth 1 https://github.com/showmethecold/effective-java-skillWhat 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 | $0.00064 | $0.00111 |
| Opus 5 | $0.00032 | $0.00056 |
| Sonnet 5 | $0.00013 | $0.00022 |
| Haiku 4.5 | $0.00006 | $0.00011 |
Grade A, and why
apply-effective-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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 11 lines · 64 tokens per session scan A 5d2958a7bbd3
apply-effective-java is a skill published in the GitHub repository showmethecold/effective-java-skill (1 stars, last pushed 3mo ago), with no licence file. It adds 64 tokens to every session and 111 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 2026-08-31.
Other skills, from other repositories
flyway-safe-migration
Review Flyway SQL migrations for PostgreSQL or MySQL production safety. Use when creating or reviewing versioned or repeatable migration files, pull requests with DDL or backfills, zero-downtime schema changes, expand-contract rollouts, index creation, constraint validation, type changes, renames, or destructive…
jpa-query-reviewer
Review Spring Data JPA and Hibernate code for query count, fetching, pagination, transaction, locking, and persistence-context risks. Use for entity mappings, repositories, JPQL or native SQL, Specifications, DTO projections, service methods, REST serialization, or reports of N+1 queries, LazyInitializationException…
jvm-incident-triage
Triage live or captured JVM incidents using thread dumps, GC logs, heap and native-memory evidence, JFR recordings, application metrics, and operating-system signals. Use for high CPU, hangs, deadlocks, latency, allocation pressure, long GC pauses, memory leaks, native OOM, or repeated JVM restarts.
maven-dependency-upgrader
Plan and validate safe Maven dependency, plugin, BOM, Java, Spring Boot, Spring Cloud, or Spring AI upgrades. Use when resolving version drift, CVE remediation, convergence errors, removed APIs, Jakarta migration, build plugin compatibility, or multi-module upgrade sequencing.
spring-ai-tool-reviewer
Review Spring AI @Tool methods and ToolCallback implementations for safe, predictable agent execution. Use when creating or reviewing tool descriptions, parameter schemas, side effects, authorization, approval gates, idempotency, timeouts, retries, error handling, observability, sensitive output, or tool-focused tests.
spring-boot-failure-analyzer
Diagnose Spring Boot application startup and ApplicationContext failures. Use when logs or code show BeanCreationException, circular dependencies, configuration binding or validation errors, missing beans, failed conditional auto-configuration, profile or property problems, or port conflicts; do not use for…