Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aliyun/alibabacloud-adb-mysql-mcp-servernpx agentmods add skills/aliyun/alibabacloud-adb-mysql-mcp-server/alibabacloud-adb-knowledgeWrote 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/aliyun/alibabacloud-adb-mysql-mcp-server/alibabacloud-adb-knowledge)<a href="https://agentmods.dev/skills/aliyun/alibabacloud-adb-mysql-mcp-server/alibabacloud-adb-knowledge"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-adb-mysql-mcp-server/alibabacloud-adb-knowledge/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/aliyun/alibabacloud-adb-mysql-mcp-server/alibabacloud-adb-knowledge"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-adb-mysql-mcp-server/alibabacloud-adb-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 43 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00100 | $0.02566 |
| Opus 5 | $0.00050 | $0.01283 |
| Sonnet 5 | $0.00020 | $0.00513 |
| Haiku 4.5 | $0.00010 | $0.00257 |
Grade A, and why
alibaba-adb-knowledge 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADB Knowledge
Run aliyun commands directly. Do not create, invoke, or depend on a wrapper script.
Read README.md when the user needs CLI installation, credential setup, permissions, or a complete end-to-end walkthrough.
End-to-end workflow
Every task that involves uploading or ingesting files must follow these four steps in strict order:
- Environment check — Verify the CLI, ADB plugin, and required parameters are available (see "Install and verify the CLI").
- Bucket selection — Execute
list-lake-storages, extractItems[].LakeStorageId, present those values to the user, and let them choose exactly one bucket. This is a mandatory prerequisite; do not skip it or assume a bucket. - Upload + Ingest — Upload the file(s) to OSS → verify with
aliyun oss stat→ immediately executeadd-knowledge-file. These three actions are a single atomic sequence; do not wait for a separate user instruction between them. - Recall —
get-knowledge-recallwith full raw output returned verbatim.
Step 2 (Bucket selection) is an independent prerequisite that must complete before any upload or ingestion operation begins.
Path validation
Every OSS target path (for upload) and every --file-location value (for ingestion) must start with oss://adb-lake-. This ensures only lake-storage buckets are used.
Before executing aliyun oss cp or aliyun adb add-knowledge-file, validate the resolved OSS URI:
- ✅
oss://adb-lake-cn-beijing-9746ll8740/knowledge/report.pdf— valid - ❌
oss://my-custom-bucket/knowledge/report.pdf— rejected
If the path does not match the oss://adb-lake- prefix, stop immediately and inform the user that only lake-storage buckets (prefixed with adb-lake-) are supported. Do not proceed with upload or ingestion.
Constants and configuration
Use API version 2021-12-01 for every ADB knowledge command.
Require the ADB cluster ID. Prefer ADB_INSTANCE_ID when it is available:
export ADB_INSTANCE_ID="amv-xxxxxxxxxxxxxx"
What ships with it
2 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.
- 12d ago First seen · 223 lines · 100 tokens per session scan A e5429ed5551b
alibaba-adb-knowledge is a skill published in the GitHub repository aliyun/alibabacloud-adb-mysql-mcp-server (32 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 2,566 once invoked, about $0.0005 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
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
azure-search-documents-ts
Build search applications using Azure AI Search SDK for JavaScript (@azure/search-documents). Use when creating/managing indexes, implementing vector/hybrid search, semantic ranking, or building agentic retrieval with knowledge bases.
convex-agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
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.
langchain4j-spring-boot-integration
Provides integration patterns for LangChain4j with Spring Boot. Configures AI model beans, sets up chat memory with Spring context, integrates RAG pipelines with Spring Data, and handles auto-configuration, dependency injection, and Spring ecosystem integration. Use when embedding LangChain4j into Spring Boot…
azure-search-documents-py
Full-text, vector, and hybrid search with AI enrichment capabilities.