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 LnYo-Cly/ai4j --skill ai4j-app-buildergit clone --depth 1 https://github.com/LnYo-Cly/ai4jWrote 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/lnyo-cly/ai4j/ai4j-app-builder)<a href="https://agentmods.dev/skills/lnyo-cly/ai4j/ai4j-app-builder"><img src="https://agentmods.dev/badge/skills/lnyo-cly/ai4j/ai4j-app-builder/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/lnyo-cly/ai4j/ai4j-app-builder"><img src="https://agentmods.dev/badge/skills/lnyo-cly/ai4j/ai4j-app-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 21 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00120 | $0.01066 |
| Opus 5 | $0.00060 | $0.00533 |
| Sonnet 5 | $0.00024 | $0.00213 |
| Haiku 4.5 | $0.00012 | $0.00107 |
Grade A, and why
ai4j-app-builder 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 11d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI4J App Builder
Purpose
Use this Skill as the user-side AI4J app-building copilot. It is for people who want to use AI4J in their own Java or Spring Boot application, not for maintaining the AI4J SDK repository.
The agent should reduce integration cost by choosing the smallest correct AI4J dependency, writing a minimal runnable vertical slice, keeping secrets out of code, and proving the result with a local verification step.
Repository maintenance is outside this Skill's ownership. Read AGENTS.md and use the repository's Harness Anything (ha) task, evidence, review, and completion flow.
Startup Workflow
- Identify the target project type: plain Java, Maven module, Spring Boot app, existing app, demo/prototype, RAG app, MCP integration, Agent app, Coding Agent host, or FlowGram backend.
- Inspect existing build/config files when available (
pom.xml,build.gradle,application.yml, controller/service layout). If no project exists, ask only for the missing minimum: Java version, build tool, app type, provider/model. - Choose the smallest AI4J module path. Read
references/app-paths.mdwhen selecting dependencies or deciding between core SDK, starter, agent, coding, and FlowGram modules. - Add configuration through environment variables or local config placeholders. Never hardcode API keys, access tokens, private endpoints, or one-person machine paths.
- Implement one thin end-to-end slice before adding features: dependency -> config -> service call -> returned text/result -> verification.
- Run or provide the smallest useful verification command. Read
references/verification.mdfor build/test, live-provider, and troubleshooting patterns.
Module Selection Rules
- Use
ai4jfor plain Java, library code, CLI tools, first chat, streaming, tool/function calls, MCP client/server, embeddings, rerank, image/audio/realtime, memory, and RAG. - Use
ai4j-spring-boot-starterfor Spring Boot apps that should injectAiServicefromai.*configuration. - Add
ai4j-agentonly when the app needs agent runtime concepts such as tool loop, memory, orchestration, trace, subagent, or team behavior. - Add
ai4j-codingonly when the app is building a coding-agent runtime or workspace-aware automation. - Use
ai4j-flowgram-spring-boot-starteronly for FlowGram workflow runtime/backend integration. - Use
ai4j-bomwhen multiple AI4J modules are used together.
What ships with it
4 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.
- 11d ago First seen · 67 lines · 120 tokens per session scan A 2ce10a82aa16
ai4j-app-builder is a skill published in the GitHub repository LnYo-Cly/ai4j (429 stars, last pushed yesterday), licensed Apache-2.0. It adds 120 tokens to every session and 1,066 once invoked, about $0.0006 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
session-rag-eval
Run and debug Chatbox session attachment RAG model evaluation with synthetic and real long-file fixtures.
bootstrap-realtime-eval
Bootstrap a new realtime eval folder inside this cookbook repo by choosing the right harness from examples/evals/realtimeevals, scaffolding prompt/tools/data files, generating a useful README, and validating it with smoke, full eval, and test runs. Use when a user wants to start a new crawl, walk, or run realtime eval…
pinecone-research
Agent RAG and long-term memory with Pinecone.
mem0-status
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.
knowledge-wiki
Manage the personal knowledge wiki. Use when the user shares articles, documents, or asks to organize knowledge; when a conversation produces insights worth preserving as structured knowledge; or when the user asks about the knowledge base.
notebooklm
Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API.…