RuoYi AI is a full-stack enterprise platform for building AI assistants and agents that combine language models, knowledge bases, visual workflows, and multiple cooperating agents. Developers and organizations use it to manage model providers, retrieve information from documents, connect tools through MCP, and orchestrate agent workflows. The catalogue includes skills for working with RuoYi AI.
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 ageerle/ruoyi-ai --skill repository-investigationgit clone --depth 1 https://github.com/ageerle/ruoyi-aiWrote 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/ageerle/ruoyi-ai/repository-investigation)<a href="https://agentmods.dev/skills/ageerle/ruoyi-ai/repository-investigation"><img src="https://agentmods.dev/badge/skills/ageerle/ruoyi-ai/repository-investigation/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/ageerle/ruoyi-ai/repository-investigation"><img src="https://agentmods.dev/badge/skills/ageerle/ruoyi-ai/repository-investigation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00441 |
| Opus 5 | $0.00024 | $0.00220 |
| Sonnet 5 | $0.00010 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
repository-investigation 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 12d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository investigation
Build a focused evidence map before proposing or applying a change. The purpose is to make the first edit land on the real ownership boundary instead of the first matching string.
Workflow
- Restate the observable behavior, constraint, and desired outcome in one short internal goal.
- Discover repository instructions and the build/runtime entry points.
- Search for identifiers, routes, events, configuration keys, and tests before opening large files.
- Trace one complete path from input to state transition or side effect and then to its consumer.
- Identify persistence, concurrency, authentication, cancellation, and error boundaries that affect the change.
- Inspect relevant history only when current code leaves an architectural decision unexplained.
- Record a compact evidence map: owning files, data flow, invariants, existing tests, and unresolved assumptions.
- Use the evidence map to decide whether the task is simple enough to act directly or needs an explicit plan.
Investigation discipline
- Prefer targeted search and line ranges over recursively loading whole source trees.
- Distinguish an interface or prompt claim from a production call site that actually uses it.
- Verify both writers and readers of persisted or streamed state.
- For asynchronous behavior, locate lifecycle ownership, queue semantics, cancellation, reconnect, and recovery.
- For security-sensitive behavior, trace authenticated identity all the way to the resource and side effect.
- Treat generated files, build output, vendored dependencies, and comments as secondary evidence unless they are the runtime source of truth.
Output to the running task
Keep the result concise and actionable:
- operative request and constraints;
- ownership/data-flow map with paths;
- invariants the implementation must preserve;
- tests and commands that can prove the result;
- assumptions that require user input or runtime evidence.
Do not turn the investigation into a generic repository summary. Stop when the evidence is sufficient to make the next decision safely.
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.
- 12d ago First seen · 41 lines · 49 tokens per session scan A 3df7e8d7409f
repository-investigation is a skill published in the GitHub repository ageerle/ruoyi-ai (5,690 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 441 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
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
ask-user-question
Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.
pixelbrowse
Screenshot and visually read any web page or document using pixelshot. Use instead of fetching raw HTML when you need to see what a page looks like, read visual content (charts, diagrams, infographics), check layouts, or verify UI. Triggers: "look at this page", "screenshot", "what does this site look like", "check…
memos-memory-guide
Use the MemOS Local memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query…