oceanbase-mcp: Skill for OpenCode

.opencode/skills/oceanbase-query/SKILL.md

oceanbase-query is a skill for OpenCode from sevoniva-labs/oceanbase-mcp. It costs 34 tokens per session (1,167 once invoked), scanned A, original, Apache-2.0.

A guide for querying OceanBase, a database compatible with MySQL, through OceanBase MCP tools. It requires checking database metadata before writing read-only SQL.

In plain words
What is it for?
Use it to find tables and columns, understand schemas and relationships, write and preview read-only SQL, inspect query plans, generate entity-relationship diagrams, and document results.
Why use it?
It helps prevent queries based on wrong tables, columns, or business meanings. It also adds checks for query risk, pagination, execution context, and clear result reporting.

Skill for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: mentions OpenCode.

This is sevoniva-labs/oceanbase-mcp's own configuration. It tells OpenCode how to work on oceanbase-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything oceanbase-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sevoniva-labs/oceanbase-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sevoniva-labs/oceanbase-mcp/main/.opencode/skills/oceanbase-query/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sevoniva-labs/oceanbase-mcp

Made for: OpenCode.

Wrote 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.

agentmods badge for oceanbase-query

README.md
[![agentmods](https://agentmods.dev/badge/skills/sevoniva-labs/oceanbase-mcp/oceanbase-query/github.svg)](https://agentmods.dev/skills/sevoniva-labs/oceanbase-mcp/oceanbase-query)
Your own site
<a href="https://agentmods.dev/skills/sevoniva-labs/oceanbase-mcp/oceanbase-query"><img src="https://agentmods.dev/badge/skills/sevoniva-labs/oceanbase-mcp/oceanbase-query/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.

agentmods 80×15 button for oceanbase-query

Your own site · 80×15
<a href="https://agentmods.dev/skills/sevoniva-labs/oceanbase-mcp/oceanbase-query"><img src="https://agentmods.dev/badge/skills/sevoniva-labs/oceanbase-mcp/oceanbase-query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,167 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.01167
Opus 5 $0.00017 $0.00583
Sonnet 5 $0.00007 $0.00233
Haiku 4.5 $0.00003 $0.00117

Measured 10d ago against content hash 291b5141c4d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

oceanbase-query 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 10d 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.

.opencode/skills/oceanbase-query/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Use this skill when a user asks to inspect OceanBase schemas, understand tables, write read-only SQL, query data, explain results, analyze a query plan, generate ER diagrams, review metadata changes, or produce data documentation.

Workflow

  1. Search metadata before writing SQL.
  2. Read table context, schema map, or onboarding documentation before choosing columns or joins.
  3. Prepare or build only read-only SQL with explicit columns.
  4. Lint or preview policy and plan risk before execution.
  5. Query with a session and pagination when inspecting data.
  6. Summarize rows, filters, page state, warnings, and next steps.

Metadata First

Use these tools before SQL:

  • ob_search_everything for business terms, table names, column names, comments, and glossary hits.
  • ob_search_business_glossary for configured business-term mappings. Treat results as hints and verify with metadata tools.
  • ob_get_schema_map, ob_find_tables_by_business_term, and ob_find_columns to narrow candidate tables and fields.
  • ob_get_table_context, ob_get_table_summary, or ob_generate_onboarding_doc for table structure, relationships, query entry points, and glossary hints.
  • Existing metadata tools as fallback: ob_get_table_ddl, ob_describe_table, ob_get_indexes, ob_get_constraints, ob_get_partitions, ob_get_table_stats, ob_find_related_tables, and ob_generate_query.

Never invent table names, fields, joins, or relationships. If metadata is insufficient, ask for the business term, schema, or table name.

Query Rules

  • Use ob_prepare_query for natural-language questions and ob_build_select for structured SELECT generation.
  • Use ob_lint_sql or ob_query_preview before executing a user-facing query.
  • Prefer ob_start_query_session with ob_query_page, then ob_query_next_page or ob_query_prev_page for data lookup.
  • Use ob_query only with explicit selected columns, filters, ordering, and a small limit.
  • Use ob_profile_table, ob_profile_columns, ob_get_value_distribution, ob_detect_time_columns, and ob_detect_dimension_columns for data understanding.
  • Use ob_policy_explain when checking whether SQL is allowed.
  • Use ob_analyze_query_plan or ob_generate_performance_report for performance questions.

Read the full file on GitHub · 87 lines

Changes

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.

  1. 10d ago First seen · 87 lines · 34 tokens per session scan A 291b5141c4d8

Subscribe to this mod's changes

oceanbase-query is a skill published in the GitHub repository sevoniva-labs/oceanbase-mcp (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,167 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 2026-08-31.

Related

Other skills, from other repositories

draft-release-notes

Author the committed release-notes file for a Prisma 8 release (stable or 8.0.0-rc.N) by enumerating the merged PRs since the previous release v tag (stable or -rc.N), resolving opaque TML-NNNN: titles via Linear context (never copied verbatim), triaging public-worthiness, and writing categorized notes — breaking…

prisma/orm · 174 tokens

record-upgrade-instructions

Record upgrade instructions alongside a Prisma Next breaking-change PR, so downstream consumers (users of @internal/ and authors of Prisma Next extensions) can apply the matching code translation automatically via the published upgrade skills. Use when you have refactored framework code and the test suite went red in…

prisma/orm · 120 tokens

create-pr

Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.

prisma/orm · 47 tokens

triage-contributor-pr

Triage open pull requests from external contributors to prisma/prisma and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…

prisma/orm · 131 tokens

contrib-pr

Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.

prisma/orm · 65 tokens

github-review-iteration

Orchestrates a GitHub PR review loop by delegating triage and implementation to dedicated sub-agents, then repeating until actionable review items are cleared. Use when the user says “address PR review”, “triage review comments”, or “iterate until review is clean”.

prisma/orm · 60 tokens