A governed operations toolkit for MySQL 8.x and MariaDB 10.6+, databases that store and query application data. It provides read and write tools for checking servers, diagnosing issues, and carrying out database administration.

Use it to inspect server health, connections, variables, status, databases, sessions, slow queries, locks, replication, and storage; it also supports selected administrative changes.

It brings common database checks and investigations into one workflow while recording actions in a local audit log and protecting stored credentials. It can help investigate slow queries, lock waits, replication, and storage fragmentation.

mysql-aiops — Skill for Claude Code by AIops-tools

Install

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.

Any agent

npx skills add AIops-tools/MySQL-AIops --skill mysql-aiops

Clone the repo

git clone --depth 1 https://github.com/AIops-tools/MySQL-AIops

Made for: Claude Code.

Or install mysql-aiops, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aiops-tools/mysql-aiops/mysql-aiops/github.svg)](https://agentmods.dev/skills/aiops-tools/mysql-aiops/mysql-aiops)

Your own site

<a href="https://agentmods.dev/skills/aiops-tools/mysql-aiops/mysql-aiops"><img src="https://agentmods.dev/badge/skills/aiops-tools/mysql-aiops/mysql-aiops/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aiops-tools/mysql-aiops/mysql-aiops"><img src="https://agentmods.dev/badge/skills/aiops-tools/mysql-aiops/mysql-aiops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 490 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,633 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.

Model	Per session	Once invoked
Fable 5.1	$0.00490	$0.04633
Opus 5.5	$0.00196	$0.01853
Sonnet 5.5	$0.00098	$0.00927
Haiku 4.5	$0.00049	$0.00463

Measured 7d ago against content hash 8799c4caa664, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mysql-aiops 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 7d 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.

skills/mysql-aiops/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MySQL AIops

Audit availability: Real writes require a durable audit intent. Reads and previews can continue if audit storage fails; check the warning and audit health before relying on their audit trail.

Disclaimer: Community-maintained open-source project, not affiliated with, endorsed by, or sponsored by Oracle Corporation or the MariaDB Foundation. "MySQL" and "MariaDB" trademarks belong to their owners. Source at github.com/AIops-tools/MySQL-AIops under the MIT license.

Governed MySQL / MariaDB DBA operations — 35 MCP tools, every one wrapped with the bundled @governed_tool harness: a local unified audit log under ~/.mysql-aiops/, token/runaway budget guard, undo-token recording, and descriptive risk-tier labels. The account password is stored encrypted (~/.mysql-aiops/secrets.enc, Fernet + scrypt) — never plaintext on disk.

Standalone: the governance harness is bundled in the package (mysql_aiops.governance) — mysql-aiops has no external skill-family dependency. Behaviour is covered by a mock-based test suite; docs/VERIFICATION.md is the checklist for a live run against a real MySQL / MariaDB server.

What This Skill Does

Domain	Tools	Count	Read or Write
Overview	server health snapshot (version+flavor, connections, replica role)	1	1 read
Server	version+flavor, variables, status, databases, engines, connection stats	6	6 read
Activity	sessions, long-running queries, transactions, lock waits	4	4 read
Queries	top-N statement digests, EXPLAIN FORMAT=JSON	2	2 read
Indexes	unused, redundant/duplicate, cardinality stats	3	3 read
Tables	sizes, data_free fragmentation, engine/row-format status	3	3 read
Replication	replica status/lag, binlog/GTID	2	2 read
Analysis (flagship)	slow-query RCA, lock-wait & deadlock RCA, replication-lag RCA, fragmentation	4	4 read
Writes	kill-session, kill-query, drop-index	3	3 write (high)
	optimize, analyze-table, create-index, SET GLOBAL, reset-stats	5	5 write (medium)
Undo	undo list, undo apply	2	1 read / 1 write

Read the full file on GitHub · 224 lines

Files

What ships with it

4 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.

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.

7d ago Changed · +2 lines 8799c4caa664
1mo ago Changed 8bf3004ba8a2
1mo ago Changed · +9 lines 4e076655af70
2mo ago First seen · 213 lines · 490 tokens per session scan A 25ea203e8bf6

Subscribe to this mod's changes

mysql-aiops is a skill published in the GitHub repository AIops-tools/MySQL-AIops (0 stars, last pushed 7d ago), licensed MIT. It adds 490 tokens to every session and 4,633 once invoked, about $0.0020 per session on Opus 5.5. 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.

Databases agent-skills ai-ops aiops governance mariadb mcp mysql

mysql-aiops next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mysql-aiopsAIops-tools/MySQL-AIops	Skill	0	7d ago	MIT	A	490	Claude Code
postgres-aiopsAIops-tools/Postgres-AIops	Skill	0	7d ago	MIT	A	443	Claude Code
queue-aiopsAIops-tools/Queue-AIops	Skill	0	7d ago	MIT	A	339	Claude Code
mysqlericrisco/rsc-harness	Skill	503	2d ago	MIT	A	116	Claude Code, Codex
mysql-expertpersonamanagmentlayer/pcl	Skill	44	11d ago	Apache-2.0	A	99	Claude Code
container-host-aiopsAIops-tools/Container-Host-AIops	Skill	1	7d ago	MIT	A	470	Claude Code
firewall-aiopsAIops-tools/Firewall-AIops	Skill	1	7d ago	MIT	A	378	Claude Code