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/kajitiluna/erd-designerWrote 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/kajitiluna/erd-designer/agent-plugin)<a href="https://agentmods.dev/plugins/kajitiluna/erd-designer/agent-plugin"><img src="https://agentmods.dev/badge/plugins/kajitiluna/erd-designer/agent-plugin/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/kajitiluna/erd-designer/agent-plugin"><img src="https://agentmods.dev/badge/plugins/kajitiluna/erd-designer/agent-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
erd-designer 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 yesterday.
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
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "erd-designer",
"description": "Design and edit ERD Designer (.erd) files with an agent. Provides a bundled CLI and a skill so agents can add tables, columns and relations, and export DDL without the MCP server.",
"version": "0.261017.224854",
"author": {
"name": "kajitiluna"
},
"homepage": "https://github.com/kajitiluna/erd-designer",
"repository": "https://github.com/kajitiluna/erd-designer",
"license": "Apache-2.0",
"keywords": [
"erd",
"er-diagram",
"database",
"database-design",
"schema-design",
"ddl",
"sql",
"mcp",
"claude-code",
"agent-skills"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 75 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.
- yesterday Changed c15b226b1c1d
- 8d ago Changed 1eee07806a41
- 15d ago Changed fa2dfb30603c
- 26d ago Changed 1e7d1568a69b
- 1mo ago Changed 16db117ebff3
- 1mo ago Changed eb8f7a60ab8c
- 1mo ago First seen · 25 lines scan A 387535837ee7
erd-designer is a plugin published in the GitHub repository kajitiluna/erd-designer (27 stars, last pushed yesterday), licensed Apache-2.0. 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
migrate-tool
Generate database migrations and code migration scripts for framework upgrades.
cloud-sql-sqlserver
Connect to Cloud SQL for SQL Server.
materialize
Materialize agent skills: docs, dbt, Terraform, mz-deploy, health checks, freshness debugging, memory tuning, and live demo data.
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.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.