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 skills add vaquarkhan/Fullstack-development-agent-skills --skill java-agent-coregit clone --depth 1 https://github.com/vaquarkhan/Fullstack-development-agent-skillsWrote 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/vaquarkhan/fullstack-development-agent-skills/java-agent-core)<a href="https://agentmods.dev/skills/vaquarkhan/fullstack-development-agent-skills/java-agent-core"><img src="https://agentmods.dev/badge/skills/vaquarkhan/fullstack-development-agent-skills/java-agent-core/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/vaquarkhan/fullstack-development-agent-skills/java-agent-core"><img src="https://agentmods.dev/badge/skills/vaquarkhan/fullstack-development-agent-skills/java-agent-core.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 | $0.00049 | $0.00576 |
| Opus 5.5 | $0.00020 | $0.00230 |
| Sonnet 5.5 | $0.00010 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
java-agent-core 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Java Agent Core
Use When
- Building autonomous or semi-autonomous agents on Spring Boot
- Orchestrating multi-step LLM workflows with tools, memory, and guardrails
- Exposing agent capabilities via REST, messaging, or MCP
Workflow
- Define agent goals, tool catalog, and memory scope (session vs user vs tenant).
- Choose orchestration style: single ChatClient loop, state machine, or workflow engine.
- Register tools with typed inputs/outputs; enforce idempotency on side-effecting tools.
- Add guardrails: max iterations, token budget, timeout, human-in-the-loop checkpoints.
- Instrument traces, token usage, and tool-call audit logs per request.
- Validate with replay tests and adversarial prompt cases.
Required Checks
- Tool handlers are idempotent or explicitly documented as non-idempotent
- Secrets and API keys loaded from environment/vault — never hardcoded
- Agent loop has max-iteration and timeout bounds
- Side-effecting tools require authorization and audit logging
- Memory scoped per user/session with explicit retention policy
Examples And Templates
See examples/ for side-by-side good vs bad patterns agents commonly get wrong.
See templates/ for copy-paste starters aligned with this skill.
Decision Framework
- Prefer Spring AI ChatClient + advisors for LLM calls; MCP for external tool protocol.
- Keep tool implementations thin — delegate business logic to @Service layer.
- Use structured output (.entity()) for machine-parseable agent decisions.
- Separate planning from execution when financial, auth, or data-deletion tools are involved.
Common Rationalizations And Rebuttals
- "One big prompt handles everything." -> Unbounded prompts drift; use tool registry and structured steps.
- "Agents can call repositories directly." -> Tools must go through services with auth and transaction boundaries.
- "Memory can be global." -> Cross-user memory leaks data; scope memory with conversationId per principal.
Evidence Pack
- Agent architecture diagram: orchestrator, tools, memory, guardrails
- Tool catalog with input schema, auth requirements, and idempotency notes
- Token/latency metrics and sample trace for a multi-step run
- Adversarial test results (prompt injection, tool misuse attempts)
What ships with it
3 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.
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 · 62 lines · 49 tokens per session scan A 9ee11170d973
java-agent-core is a skill published in the GitHub repository vaquarkhan/Fullstack-development-agent-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 576 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 2026-08-31.
Other skills, from other repositories
ruoyi-cloud
Use when scaffolding Java Spring Cloud microservice backends — Nacos service discovery, Sentinel rate limiting, Seata distributed transactions, Spring Boot 3 + Vue 3 admin. RuoYi-Cloud: popular Chinese Spring Cloud microservice boilerplate framework.
spring-boot-4-conventions
Spring Framework 7 / Spring Boot 4 idioms and defaults. Use when writing or reviewing controllers, services, configuration, HTTP clients, async/virtual-thread code, or anything touching Spring's programming model.
others-skills
Use when needing Go language development, desktop RPA automation, self-hosted email marketing, Java Spring Cloud scaffolding, SSL/TLS certificate automation, Docker Compose multi-container orchestration, or building a bilingual children's Phaser/Vue game collection. Index of 8 skills: Go, RobotGo, RobotGo-Flow…
spring-boot
Spring Boot 3.x - Java framework for production-ready applications with dependency injection, REST APIs, data access, security, and actuator monitoring.
quarkus-expert
High-performance Quarkus framework expertise covering reactive patterns, CDI, build-time augmentation, and cloud-native development. Use for general Quarkus questions.
spring-boot-development
Comprehensive Spring Boot development skill covering auto-configuration, dependency injection, REST APIs, Spring Data, security, and enterprise Java applications.