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 agentmods add instructions/weejar/oceanbase-skills/claude-mdgit clone --depth 1 https://github.com/weejar/oceanbase-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/instructions/weejar/oceanbase-skills/claude-md)<a href="https://agentmods.dev/instructions/weejar/oceanbase-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/weejar/oceanbase-skills/claude-md.svg" alt="Measured on agentmods" 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 | $0.01357 | $0.01357 |
| Opus 5 | $0.00678 | $0.00678 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
oceanbase-skills CLAUDE.md 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 5d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Guidance for Claude Code (and other AI coding agents)
Skill Set Overview
This directory contains 96 reference guides for OceanBase Database. Each file is a self-contained reference on one specific topic. Load only the file(s) relevant to the user's question.
How to Use These Skills
- Identify the category from the user's question using
AGENTS.mdrouting table - Read only the needed file(s) — do not load entire directories
- Apply the content to generate SQL, code, configurations, or explanations
- Check dual-mode notes — many topics differ between MySQL Mode and Oracle Mode
OceanBase Version Baseline
- Baseline: OceanBase V4.2 (both MySQL Mode and Oracle Mode)
- V4.4 features: marked with
> **V4.4+**: ...callout blocks - V4.5 features: marked with
> **V4.5+**: ...callout blocks - If the user does not specify a version, assume V4.2 and mention V4.4/V4.5 features as optional upgrades
Dual Compatibility Modes
OceanBase supports two compatibility modes that affect SQL syntax, data types, PL/SQL, and system views:
| Aspect | MySQL Mode | Oracle Mode |
|---|---|---|
| SQL dialect | MySQL-compatible | Oracle-compatible |
| PL/SQL | Not supported | Supported |
| Date type | DATE (no time) | DATE (with time) |
| Dual table | Not needed | SELECT 1 FROM dual |
| Empty string | ='' is true |
='' is NULL |
| System views | information_schema |
DBA_*, USER_*, ALL_* |
When generating code or SQL, always clarify which mode the user is using if it's not obvious from context.
Key Concepts Unique to OceanBase
- Tenant: Isolation unit (like a database instance). Each tenant has its own resource units.
- Resource Unit (Unit): Hardware resource definition (CPU, memory, disk). Assigned to zones.
- Resource Pool: Collection of resource units distributed across zones.
- Zone: Failure domain (like a data center rack). Replicas are distributed across zones.
- Paxos: Consensus protocol for log replication and leader election.
- Log Stream: Replication pipeline for a partition's redo logs.
- Tablegroup: Groups tables so that partitions with the same mapping end up on the same server (enables local joins).
- LS (Log Stream): The unit of log replication in OceanBase's distributed architecture.
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.
- 5d ago First seen · 139 lines · 1,357 tokens per session scan A a268349afafc
oceanbase-skills CLAUDE.md is an instructions file published in the GitHub repository weejar/oceanbase-skills (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,357 tokens to every session, about $0.0068 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.
Other instructions, from other repositories
lms-front CLAUDE.md
Claude Code instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, architecture and multi-tenancy.
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
rails_ai_agents AGENTS.md
AGENTS.md instructions for ThibautBaissac/rails_ai_agents, covering project configuration, tech stack, architecture, key commands and tests.
pg-dash CLAUDE.md
Claude Code instructions for indiekitai/pg-dash, covering pg-dash claude.md, 项目结构, 构建与测试, 发版纪律（强制） and 发版检查清单（每次 npm publish 前必须按序执行）.
MCP-SqlServer CLAUDE.md
Claude Code instructions for Aron-Valenzuela/MCP-SqlServer, covering claude.md, project overview, setup (for each user), 1. install dependencies and 2. configure claude desktop.