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 personamanagmentlayer/pcl --skill mysql-expertgit clone --depth 1 https://github.com/personamanagmentlayer/pclWrote 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/personamanagmentlayer/pcl/mysql-expert)<a href="https://agentmods.dev/skills/personamanagmentlayer/pcl/mysql-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/mysql-expert/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/personamanagmentlayer/pcl/mysql-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/mysql-expert.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 279 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 | $0.00099 | $0.02593 |
| Opus 5 | $0.00049 | $0.01296 |
| Sonnet 5 | $0.00020 | $0.00519 |
| Haiku 4.5 | $0.00010 | $0.00259 |
Grade A, and why
mysql-expert 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MySQL Expert
MySQL differs from PostgreSQL in ways that matter for design, not just syntax: the clustered primary key, the storage-engine boundary, and a replication model built on the binary log.
Core Concepts
InnoDB Is the Database
Everything below assumes InnoDB. Rows are stored inside the primary key index — the table is the primary key B-tree. Three consequences drive most design decisions:
- The primary key is present in every secondary index, so a wide primary key inflates every index on the table.
- A secondary index lookup costs two traversals: the index, then the primary key. Unless the index covers the query.
- Inserts in primary key order are cheap; random primary keys cause page splits and fragmentation.
This is why a BIGINT AUTO_INCREMENT or a time-ordered UUID (UUIDv7) beats a
random UUIDv4 primary key by a wide margin on large tables.
Character Sets
Use utf8mb4 and nothing else. MySQL's utf8 is a three-byte subset that cannot
store emoji or some CJK characters, and it fails by truncating or erroring at
insert time.
CREATE TABLE orders (…) ENGINE=InnoDB
DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_0900_ai_ci;
Collation determines comparison and sorting. utf8mb4_0900_ai_ci is
accent-insensitive and case-insensitive; use utf8mb4_0900_as_cs or _bin when
you need exact matching, for example on tokens or hashes.
Isolation and Locking
The default is REPEATABLE READ, which is stricter than PostgreSQL's default and
uses gap locks that surprise people migrating across.
SELECT @@transaction_isolation;
SET SESSION transaction_isolation = 'READ-COMMITTED'; -- often the better default
READ COMMITTED reduces gap locking and deadlocks for typical OLTP workloads.
Change it deliberately and test — it also changes replication semantics for
statement-based binlog formats.
Schema Design
CREATE TABLE orders (
id BIGINT UNSIGNED NOT NULL AUTO_INCREMENT,
public_id BINARY(16) NOT NULL, -- UUID stored compactly
customer_id BIGINT UNSIGNED NOT NULL,
status ENUM('pending','paid','shipped','cancelled') NOT NULL,
total_minor BIGINT NOT NULL, -- money as integer minor units
currency CHAR(3) NOT NULL,
created_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP(3),
PRIMARY KEY (id),
UNIQUE KEY uk_orders_public_id (public_id),
KEY idx_orders_customer_created (customer_id, created_at),
CONSTRAINT fk_orders_customer FOREIGN KEY (customer_id) REFERENCES customers(id)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
What ships with it
1 file 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.
- 5d ago First seen · 293 lines · 99 tokens per session scan A 137726735fae
mysql-expert is a skill published in the GitHub repository personamanagmentlayer/pcl (40 stars, last pushed 2d ago), licensed Apache-2.0. It adds 99 tokens to every session and 2,593 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 2026-09-05.
Other skills, from other repositories
mysql
Use when designing, querying, indexing or operating a MySQL or MariaDB database and engine-specific behaviour matters — schema and type choices, index design, reading EXPLAIN, online schema change, replication and replica lag, locking and InnoDB deadlocks, charset traps, and server config. NOT portable…
mysql
A guide for managing MySQL and MariaDB databases, which store application data in tables. It covers connections, users and permissions, database operations, backups, restores, and performance checks.
Database Schema Reviewer
Reviews database schemas for normalization issues, missing indexes, naming inconsistencies, and scalability risks.
database-management-patterns
Comprehensive guide for database management patterns covering PostgreSQL and MongoDB including schema design, indexing, transactions, replication, and performance tuning.
mysql-expert
Design, optimize, and maintain MySQL databases. Covers schema design, indexing strategies, query optimization, replication, and performance tuning.
graphjin-eval
Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.