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/astandrik/local-ydb-toolkitWrote 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/astandrik/local-ydb-toolkit/gemini-extension)<a href="https://agentmods.dev/plugins/astandrik/local-ydb-toolkit/gemini-extension"><img src="https://agentmods.dev/badge/plugins/astandrik/local-ydb-toolkit/gemini-extension/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/astandrik/local-ydb-toolkit/gemini-extension"><img src="https://agentmods.dev/badge/plugins/astandrik/local-ydb-toolkit/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
local-ydb-toolkit 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 28d 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": "local-ydb-toolkit",
"version": "0.1.8",
"description": "Operate Docker-based local YDB deployments with reusable safety guidance and an optional local stdio MCP server.",
"mcpServers": {
"local-ydb": {
"command": "npx",
"args": [
"--yes",
"--prefix=./.codex-plugin",
"@astandrik/[email protected]"
],
"cwd": "${extensionPath}"
}
},
"settings": [
{
"name": "Local YDB Toolkit config path",
"description": "Optional absolute path to a local-ydb-toolkit config JSON file. Leave blank to pass configPath on individual tool calls.",
"envVar": "LOCAL_YDB_TOOLKIT_CONFIG",
"sensitive": false
},
{
"name": "MCP response text format",
"description": "Optional response text format: json or toon. Leave blank for the server default.",
"envVar": "LOCAL_YDB_MCP_CONTENT_FORMAT",
"sensitive": false
}
]
}
What ships with it
38 files beside gemini-extension.json 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.
- assets/icon.svg 305 B
- examples/.gitkeep 0 B
- examples/local-ydb.config.example.json 4.3 KB
- schemas/agent-plugins/1.0.0/mcp.schema.json 3.3 KB
- schemas/agent-plugins/1.0.0/plugin.schema.json 1.8 KB
- schemas/agent-plugins/1.0.0/README.md 512 B
- schemas/agent-plugins/1.0.0/SHA256SUMS 167 B
- scripts/ci/agent-plugin-workflow.test.mjs 2.2 KB runs code
- scripts/ci/agent-plugin.test.mjs 16 KB runs code
- scripts/ci/check-agent-plugin-freshness.mjs 8.7 KB runs code
- scripts/ci/check-agent-plugin-freshness.test.mjs 12 KB runs code
- scripts/ci/Dockerfile.ssh-fixture 339 B
- scripts/ci/generate-mcp-tools-docs.mjs 3.9 KB runs code
- scripts/ci/generate-mcp-tools-docs.test.mjs 3.2 KB runs code
- scripts/ci/live-port-allocation.mjs 312 B runs code
- scripts/ci/live-port-allocation.test.mjs 585 B runs code
- scripts/ci/managed-sql-docs.test.mjs 1.6 KB runs code
- scripts/ci/managed-sql-live.mjs 9.7 KB runs code
- scripts/ci/managed-sql-live.test.mjs 14 KB runs code
- scripts/ci/mutation-diagnostics.mjs 1.3 KB runs code
- scripts/ci/mutation-diagnostics.test.mjs 5.2 KB runs code
- scripts/ci/post-release-plugin-pin.test.mjs 8.7 KB runs code
- scripts/ci/prepare-ssh-internal-grpc-fixture.mjs 21 KB runs code
- scripts/ci/release-please-config.test.mjs 2.6 KB runs code
- scripts/ci/restarting-container.mjs 1.2 KB runs code
- scripts/ci/restarting-container.test.mjs 4.0 KB runs code
- scripts/ci/skill-auth-rollout-docs.test.mjs 9.1 KB runs code
- scripts/ci/skill-credentials-docs.test.mjs 18 KB runs code
- scripts/ci/update-agent-plugin-pin.mjs 7.7 KB runs code
- scripts/ci/update-agent-plugin-pin.test.mjs 9.2 KB runs code
- scripts/ci/verify-live-mcp-server.mjs 65 KB runs code
- scripts/ci/verify-mcp-publication.mjs 8.3 KB runs code
- scripts/ci/verify-mcp-publication.test.mjs 6.0 KB runs code
- scripts/ci/verify-published-plugin-mcp.mjs 7.2 KB runs code
- scripts/ci/verify-published-plugin-mcp.test.mjs 3.2 KB runs code
- scripts/ci/verify-setup-local-ydb.mjs 2.7 KB runs code
- scripts/ci/verify-ssh-internal-grpc.mjs 13 KB runs code
- scripts/package-agent-plugin.mjs 4.6 KB runs code
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.
- 28d ago Changed 544e655396ef
- 1mo ago Changed · +1 lines ed3ea186dfd4
- 1mo ago First seen · 30 lines scan A 6f8e2cedf5e7
local-ydb-toolkit is a plugin published in the GitHub repository astandrik/local-ydb-toolkit (5 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 2026-09-08.
Other plugins, from other repositories
aicontainer
Setup aicontainer in your project.
azure-sql-database-container
Agent skills for the Azure SQL Database container, the Azure SQL Database engine running locally. Teaches your agent to run the engine, connect, migrate, scaffold, build RAG, wire CI, and go local-to-cloud, using the real Private Preview image instead of the SQL Server image.
bridge-mcp
476-tool SSH bridge for secure remote server management. Execute commands on air-gapped Linux, Windows, Docker, Kubernetes hosts via SSH from Claude Code.
container-host-aiops
Governed Docker + Portainer container-host ops: reads, RCA analyses, guarded writes. 38 tools.
pibox
pi-coding-agent running in a container: interactive shell, one-shot exec, an HTTP REST API, an OpenAI-compatible chat endpoint, an MCP server, a Telegram bot, and a cron scheduler, all on one image.
typo3-ddev
DDEV setup for TYPO3 extension development.