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 astandrik/local-ydb-toolkit --skill local-ydbgit 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/skills/astandrik/local-ydb-toolkit/local-ydb)<a href="https://agentmods.dev/skills/astandrik/local-ydb-toolkit/local-ydb"><img src="https://agentmods.dev/badge/skills/astandrik/local-ydb-toolkit/local-ydb/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/astandrik/local-ydb-toolkit/local-ydb"><img src="https://agentmods.dev/badge/skills/astandrik/local-ydb-toolkit/local-ydb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00108 | $0.03427 |
| Opus 5 | $0.00054 | $0.01714 |
| Sonnet 5 | $0.00022 | $0.00685 |
| Haiku 4.5 | $0.00011 | $0.00343 |
Grade A, and why
local-ydb 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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local YDB
Purpose
Use this skill to inspect, document, run, harden, troubleshoot, or generate and apply table schemas for local-ydb deployments. Keep reusable operational recipes separate from one-off cutover notes, host paths, timestamps, and secrets.
Execution Boundary
- Operate a deployment only when the active agent has a local shell or the
local_ydb_*MCP tools connected to the target machine. A chat-only or remote environment cannot inspect the user's Docker daemon, files, or YDB endpoints. - When local execution is unavailable, provide a bounded plan, configuration guidance, or commands for the user to run. State that the target was not inspected and do not report inferred health, inventory, or mutation results as observed facts.
- Plugin MCP processes start from the installed plugin root. Pass an absolute
configPathto profile-based tools or configureLOCAL_YDB_TOOLKIT_CONFIGin the MCP client; do not assume a project-locallocal-ydb.config.jsonis the process working-directory default. - Keep every mutation plan-first regardless of execution surface. Require the existing confirmation boundary before applying changes and preserve rollback and verification steps.
First Steps
- Identify the task type: documentation cleanup, local bootstrap, live inspection, managed YQL query/explain/execute, schema generation/apply, auth hardening, storage expansion, monitoring exposure, TLS investigation, or troubleshooting.
- Determine whether the target is repo documentation, a local Docker stack, or a live remote host. Treat live Docker/YDB changes as medium to high risk; collect read-only state first and ask before destructive or externally visible mutations.
- Check nearby project docs before editing reusable runbooks. Prefer existing setup, runbook, and auth notes over inventing a new topology.
- Keep secrets and private host details out of public docs and skill output. Use placeholders for password files, private keys, IPs, domains, users, and backup paths unless the user explicitly asks for private operational notes.
What ships with it
9 files 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.
- 9d ago First seen · 92 lines · 108 tokens per session scan A b3d24c485829
local-ydb is a skill published in the GitHub repository astandrik/local-ydb-toolkit (4 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 3,427 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 2026-08-31.
Other skills, from other repositories
weaviate-local-setup
Set up and manage a local Weaviate instance using Docker.
infra-ops
How to operate live infrastructure safely — servers, SSH, deployments, databases, containers, incidents and outages. Use when the operator asks to deploy, restart, migrate, debug a production problem, run something on a remote host, or touch a database.
convex-migration-helper
Plans Convex schema and data migrations with widen-migrate-narrow and @convex-dev/migrations. Use for breaking schema changes, backfills, table reshaping, or zero-downtime rollouts.
convex-expert
Convex backend specialist. Use this agent for any code inside a convex/ directory — function definitions, schemas, indexes, queries, mutations, actions, HTTP endpoints, cron jobs, file storage, auth wiring, and component installation. Knows the object-form function syntax, validator patterns, resource limits, and…
convex-design
Design and build reactive, type-safe, production-grade backends on Convex. Covers schema, queries/mutations/actions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM/agent workflows on Convex's one-platform stack.
convex-explain-app
Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.