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 magnus919/agent-skills --skill spring-aigit clone --depth 1 https://github.com/magnus919/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/magnus919/agent-skills/spring-ai)<a href="https://agentmods.dev/skills/magnus919/agent-skills/spring-ai"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/spring-ai/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/magnus919/agent-skills/spring-ai"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/spring-ai.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 | $0.00080 | $0.00966 |
| Opus 5.5 | $0.00032 | $0.00386 |
| Sonnet 5.5 | $0.00016 | $0.00193 |
| Haiku 4.5 | $0.00008 | $0.00097 |
Grade A, and why
spring-ai 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spring AI
Use this operational skill to inspect a real Maven or Gradle Spring AI project before changing it. The included diagnostic CLI is offline and provider-neutral: it reads build files, application configuration, and source to report compatibility clues, unsafe defaults, missing conversation IDs, streaming prerequisites, tool/MCP boundaries, retrieval configuration, and observability risks. It never sends prompts or exposes API-key values.
Entry check
Confirm the project root and whether the task is read-only or will modify configuration/code. Read-only diagnosis can proceed. Before the first state-changing action, confirm the target project, scope, and rollback path (usually a reviewed commit or revert); the CLI itself is read-only.
Run:
python3 spring-ai/scripts/spring_ai_check.py --root /path/to/project --json
The result is stable JSON with status, project, facts, findings, and errors. Exit 0 means no error-severity finding; exit 1 means an error-severity finding or warnings promoted by --strict; exit 2 means an invalid invocation or unreadable project.
Workflow
- Run the checker and retain its JSON output with the project revision.
- Resolve build compatibility findings against the official Spring AI and Spring Boot documentation in
references/source-index.md; do not infer support from a transitive dependency alone. - Inspect ChatClient advisor order and parameters. Every memory-advisor call needs an explicit conversation identifier derived from the application’s authenticated/session boundary; never use a shared default.
- For retrieval, verify document ownership/authorization before retrieval context enters a prompt. Test empty retrieval, stale data, provider errors, and latency separately.
- For tools and MCP, treat model tool requests as untrusted proposals. The application owns authorization and execution. Bound tool names, arguments, timeout, retry, side effects, and audit fields. Verify MCP transport and schema against the current project dependency.
- For streaming, preserve partial output as provisional until completion; test cancellation, timeout, disconnect, and failed completion. Do not treat a partial stream as a committed answer or side effect.
- Keep prompt/completion logging disabled by default in production. If enabled temporarily, document redaction, access, retention, and rollback.
- Run the project’s own tests/build when dependencies and provider credentials are available. The checker does not prove provider connectivity, model quality, RAG correctness, or production readiness.
What ships with it
10 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.
- evals/evals.json 3.9 KB
- examples/minimal-project/pom.xml 890 B
- examples/minimal-project/src/main/java/example/Demo.java 229 B
- examples/minimal-project/src/main/resources/application.properties 151 B
- README.md 2.3 KB
- references/compatibility-and-setup.md 2.1 KB
- references/integration-boundaries.md 2.1 KB
- references/source-index.md 1.6 KB
- scripts/spring_ai_check.py 14 KB runs code
- scripts/test_spring_ai_check.py 8.9 KB runs code
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 · 59 lines · 80 tokens per session scan A 6d3884a58878
spring-ai is a skill published in the GitHub repository magnus919/agent-skills (133 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 966 once invoked, about $0.0003 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 2026-09-15.
Other skills, from other repositories
serving-llms-vllm
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
data-leakage-detection
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.
bridging-presidio-and-spacy
Combine OpenMed clinical NLP with Microsoft Presidio, spaCy, or LangChain through OpenMed's built-in interop adapter registry (openmed.interop). Covers the lazy adapter registry (availableadapters, getadapter, adapterspec), the presidio/spacy/langchain pip extras, and the verified callables — Presidio…
server-inference
Use this skill when the user wants to run or debug MLX-VLM server inference, including uv run mlxvlm.server, /v1/models, /v1/chat/completions, /v1/responses, streaming, OpenAI-compatible clients, health checks, metrics, model unload/reload, adapters, trust-remote-code, and server request/response failures.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.