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.
/plugin marketplace add sigistry/marketplacenpx agentmods add plugins/sigistry/marketplace/sql-safety-netgit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/sigistry/marketplace/sql-safety-net)<a href="https://agentmods.dev/plugins/sigistry/marketplace/sql-safety-net"><img src="https://agentmods.dev/badge/plugins/sigistry/marketplace/sql-safety-net.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
sql-safety-net 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 3d 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": "sql-safety-net",
"version": "1.0.0",
"description": "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.",
"author": {
"name": "Sigistry SQL Safety Net",
"url": "https://github.com/Sigistry/marketplace/tree/main/plugins/sql-safety-net"
},
"license": "MIT"
}
What it installs
The manifest is a name and a version. 3 skills, 5 commands, 2 agents travel with it, and installing the plugin installs all of them — 379 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill explain-interpreter A 95 tokens
- Skill safe-migrations A 98 tokens
- Skill schema-antipatterns A 93 tokens
- Command migration-safety A 19 tokens
- Command explain-plan A 21 tokens
- Command index-advisor A 19 tokens
- Command n1-scan A 18 tokens
- Command schema-review A 16 tokens
- Agent migration-rewriter A 0 tokens
- Agent n1-hunter A 0 tokens
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.
- 3d ago First seen · 11 lines scan A 5806578a91f4
sql-safety-net is a plugin published in the GitHub repository sigistry/marketplace (3 stars, last pushed 2d ago), 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 2026-09-03.
Other plugins, from other repositories
handbook-elasticsearch
Elasticsearch and Kibana REST API expertise for querying, indexing, managing indices, cluster health, aggregations, ES|QL, and dashboard deployment.
databases
Database experts for SQL, NoSQL, graph databases, and vector databases. Includes Postgres, MongoDB, Neo4j, Cassandra, MariaDB, and vector DB specialists.
quiz-me
Gates code changes behind an interactive quiz: Claude investigates, tests your understanding of root cause and fix, and only implements once you pass.
dead-code
Find and remove dead code, unused imports, and duplicates across any language.
overheid-plugins marketplace
Plugin marketplace listing 7 plugins: standaarden, zad-actions, developer-overheid, nerds, internet.
cw-debug
Generic CloudWatch log investigation skill with adaptive debugging methodology.