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 VincentChuWaiChow/vanguard-frontier-agentic --skill alibaba-polardb-rds-dbagit clone --depth 1 https://github.com/VincentChuWaiChow/vanguard-frontier-agenticWrote 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/vincentchuwaichow/vanguard-frontier-agentic/alibaba-polardb-rds-dba)<a href="https://agentmods.dev/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-polardb-rds-dba"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-polardb-rds-dba/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/vincentchuwaichow/vanguard-frontier-agentic/alibaba-polardb-rds-dba"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-polardb-rds-dba.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 | $0.00044 | $0.00624 |
| Opus 5 | $0.00022 | $0.00312 |
| Sonnet 5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
alibaba-polardb-rds-dba 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alibaba Cloud PolarDB and RDS DBA
Purpose
Act as the Alibaba Cloud database operator who maintains PolarDB clusters and RDS instances with DAS-driven diagnostics, proxy-based connection management, and documented backup and recovery postures.
When to use
Use this skill for:
- PolarDB cluster topology review: primary node and read nodes
- RDS instance sizing, engine version, and high availability configuration
- DAS (Database Autonomy Service) diagnostic findings and optimization recommendations
- Database proxy configuration for connection pooling and read/write splitting
- Global Database Network (GDN) design for cross-region PolarDB replication
- Backup policy review, recovery point objectives, and restore testing
- Query performance tuning and slow query analysis
Lean operating rules
- Prefer official Alibaba Cloud documentation and DAS evidence over memory or inference.
- Separate confirmed facts from inference. If a database state was not verified, say so.
- Challenge missing backup policies, single-node deployments without HA, and database proxy disabled for high-connection workloads.
- Keep answers scoped, traceable, and explicit about trade-offs and open questions.
- Load references only when needed; do not pull all deep guidance into short answers.
Key database guidance
- PolarDB uses shared distributed storage — adding a read node does not duplicate storage. Read scale-out is instantaneous and cost-efficient.
- PolarDB Global Database Network (GDN) replicates data across regions with sub-1-second lag. Use for geo-redundant OLTP workloads.
- DAS provides autonomous diagnostics, SQL execution plan analysis, and optimization recommendations. Always check DAS findings before manual tuning.
- Database Proxy provides built-in connection pooling and read/write splitting. Enable for workloads with high connection counts or read-heavy traffic patterns.
- PolarDB for Oracle provides Oracle syntax compatibility but has known gaps in specific PL/SQL packages — verify compatibility before migration.
- RDS supports Multi-AZ deployment for high availability — enable for all production instances.
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.
- 12d ago First seen · 63 lines · 44 tokens per session scan A 621f14fa5fae
alibaba-polardb-rds-dba is a skill published in the GitHub repository VincentChuWaiChow/vanguard-frontier-agentic (22 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 624 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
r-data
R data manipulation, formats, and database packages. Use for data wrangling with dplyr/data.table, reading files (CSV, Excel, JSON, Arrow), and database connections (SQL, MongoDB, Redis).
r-data-database
R database packages for SQL and NoSQL. Use for DBI connections, SQL queries, dbplyr, SQLite, PostgreSQL, MySQL, MongoDB, Redis.
DBI
R DBI package for database interface. Use for connecting to and querying databases with a common interface.
elastic
R elastic package for Elasticsearch. Use for connecting to Elasticsearch and performing search operations.
mongolite
R mongolite package for MongoDB. Use for connecting to MongoDB databases and performing CRUD operations.
RPostgres
R RPostgres package for PostgreSQL databases. Use for PostgreSQL connections with modern DBI interface.