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.
git clone --depth 1 https://github.com/erikdarlingdata/claude-pluginsWrote 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/plugins/erikdarlingdata/claude-plugins/sqlserver-query-plans)<a href="https://agentmods.dev/plugins/erikdarlingdata/claude-plugins/sqlserver-query-plans"><img src="https://agentmods.dev/badge/plugins/erikdarlingdata/claude-plugins/sqlserver-query-plans/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/plugins/erikdarlingdata/claude-plugins/sqlserver-query-plans"><img src="https://agentmods.dev/badge/plugins/erikdarlingdata/claude-plugins/sqlserver-query-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sqlserver-query-plans 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 1mo 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.
What it actually says
{
"name": "sqlserver-query-plans",
"displayName": "SQL Server Query Plans",
"description": "Read a SQL Server execution plan (.sqlplan / showplan XML) and explain what is actually slow, and why. Prevents the standard wrong conclusions: reading cost percentages as measurements, ranking operators by cumulative time, comparing estimated to actual rows without dividing by executions, calling scans defects, and pasting missing-index DDL verbatim.",
"version": "1.5.4",
"author": {
"name": "Erik Darling",
"email": "[email protected]",
"url": "https://erikdarling.com"
},
"homepage": "https://erikdarling.com",
"repository": "https://github.com/erikdarlingdata/claude-plugins",
"license": "MIT",
"keywords": [
"sql-server",
"mssql",
"query-plan",
"execution-plan",
"showplan",
"sqlplan",
"performance",
"query-tuning",
"tsql",
"dba"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 102 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 27 lines scan A 0283e3a58960
sqlserver-query-plans is a plugin published in the GitHub repository erikdarlingdata/claude-plugins (25 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
pgbot
Read-only, deterministic PostgreSQL diagnostics as an agent tool: health, slow queries, unused indexes, bloat, vacuum, config — findings-first, never writes.
sql-safety-net
Static, no-database-connection guardrails for schema and query work: rewrites unsafe migrations into zero-downtime expand-contract steps, hunts ORM N+1 queries in your diff, interprets pasted EXPLAIN plans, and flags schema anti-patterns.
n1-optimizer
Parallel performance analysis tool that identifies N+1 queries, inefficient APIs, and suboptimal code patterns across your entire application stack.
kolo
Kolo is a text-based Python debugger for AI agents. Capture every executed function, return value, local variable, HTTP request, and SQL query into greppable trace files.
litescope
Diagnose, migrate, monitor and repair SQLite, Cloudflare D1 and Turso databases from the agent: lock doctor, health, blast-radius previews with an undo point on every write, fleet sweeps and corruption salvage.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.