ClickHouse/agent-skills is a collection of packaged instructions that give AI coding agents specialized guidance for ClickHouse databases and chdb, an in-process version of ClickHouse for Python. It helps agents design schemas, write queries, ingest data, analyze results, and troubleshoot performance with ClickHouse or ClickHouse Cloud. The catalogue entries are the repository’s skills, plugins, and instruction for using these systems.
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 ClickHouse/agent-skills --skill clickhouse-best-practicesgit clone --depth 1 https://github.com/ClickHouse/agent-skillsWrote 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/clickhouse/agent-skills/clickhouse-best-practices)<a href="https://agentmods.dev/skills/clickhouse/agent-skills/clickhouse-best-practices"><img src="https://agentmods.dev/badge/skills/clickhouse/agent-skills/clickhouse-best-practices/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/clickhouse/agent-skills/clickhouse-best-practices"><img src="https://agentmods.dev/badge/skills/clickhouse/agent-skills/clickhouse-best-practices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00045 | $0.02532 |
| Opus 5 | $0.00023 | $0.01266 |
| Sonnet 5 | $0.00009 | $0.00506 |
| Haiku 4.5 | $0.00005 | $0.00253 |
Grade A, and why
clickhouse-best-practices 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- clickhouse-best-practices — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClickHouse Best Practices
Comprehensive guidance for ClickHouse covering schema design, query optimization, data ingestion, and AI agent connectivity. Contains 31 rules across 4 main categories (schema, query, insert, agent), prioritized by impact.
Official docs: ClickHouse Best Practices
IMPORTANT: How to Apply This Skill
Before answering ClickHouse questions, follow this priority order:
- Check for applicable rules in the
rules/directory - If rules exist: Apply them and cite them in your response using "Per
rule-name..." - If no rule exists: Use the LLM's ClickHouse knowledge or search documentation
- If uncertain: Use web search for current best practices
- Always cite your source: rule name, "general ClickHouse guidance", or URL
Why rules take priority: ClickHouse has specific behaviors (columnar storage, sparse indexes, merge tree mechanics) where general database intuition can be misleading. The rules encode validated, ClickHouse-specific guidance.
Agent Connectivity & Query Workflow
Before querying ClickHouse, agents must establish a connection and follow the discovery workflow:
rules/agent-connect-mcp.md- Connection setup (MCP + CLI), credential discovery, output format selectionrules/agent-discovery-schema.md- CRITICAL: 7-step schema discovery workflowrules/agent-query-safety.md- CRITICAL: LIMIT, timeouts, progressive exploration
Every agent session should follow this sequence:
- Connect — establish connection via MCP or CLI (see
agent-connect-mcp) - Discover — databases → tables → columns + comments → sort keys → skip indexes → sample → EXPLAIN
- Plan — use sort key and skip index knowledge to write efficient WHERE clauses
- Execute — run queries with LIMIT and timeouts
- Recover — on timeout/memory errors, narrow filters and retry (see
agent-query-safety)
Subagent architecture notes
What ships with it
36 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.
- AGENTS.md 62 KB
- metadata.json 643 B
- README.md 1.8 KB
- rules/_sections.md 1.8 KB
- rules/_template.md 624 B
- rules/agent-connect-mcp.md 4.4 KB
- rules/agent-discovery-schema.md 5.7 KB
- rules/agent-query-safety.md 5.2 KB
- rules/insert-async-small-batches.md 1.8 KB
- rules/insert-batch-size.md 1.5 KB
- rules/insert-format-native.md 933 B
- rules/insert-mutation-avoid-delete.md 2.0 KB
- rules/insert-mutation-avoid-update.md 2.1 KB
- rules/insert-optimize-avoid-final.md 1.9 KB
- rules/query-index-skipping-indices.md 2.4 KB
- rules/query-join-choose-algorithm.md 1.8 KB
- rules/query-join-consider-alternatives.md 2.1 KB
- rules/query-join-filter-before.md 1.3 KB
- rules/query-join-null-handling.md 1.0 KB
- rules/query-join-use-any.md 1.1 KB
- rules/query-mv-incremental.md 2.0 KB
- rules/query-mv-refreshable.md 2.0 KB
- rules/schema-json-when-to-use.md 2.0 KB
- rules/schema-partition-lifecycle.md 1.5 KB
- rules/schema-partition-low-cardinality.md 1.6 KB
- rules/schema-partition-query-tradeoffs.md 1.1 KB
- rules/schema-partition-start-without.md 1.2 KB
- rules/schema-pk-cardinality-order.md 1.6 KB
- rules/schema-pk-filter-on-orderby.md 1.5 KB
- rules/schema-pk-plan-before-creation.md 2.0 KB
- rules/schema-pk-prioritize-filters.md 1.2 KB
- rules/schema-types-avoid-nullable.md 1.8 KB
- rules/schema-types-enum.md 1.7 KB
- rules/schema-types-lowcardinality.md 1.7 KB
- rules/schema-types-minimize-bitwidth.md 1.4 KB
- rules/schema-types-native-types.md 1.8 KB
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.
- 12d ago First seen · 275 lines · 45 tokens per session scan A 00e4c781fd29
clickhouse-best-practices is a skill published in the GitHub repository ClickHouse/agent-skills (533 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 2,532 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
use-gfs-mcp
GFS MCP Server for AI agent integration. Provides Model Context Protocol tools for database version control with automatic schema versioning.
use-gfs-cli
Git-like version control for databases using the GFS CLI. Manage database states with commits, branches, time travel, and schema versioning.
bigquery-graph
Skill for Graph Query Language (GQL) or SQL/PGQ queries against a property graph. Includes path finding, multi-hop traversal, topological connection, shortest path, node reachability, edge connectivity, and semantic graph queries.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.
projection-patterns
Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.
dbx
DBX CLI for database schema exploration and read-only queries. When the user needs to list connections, explore tables, describe schemas, run queries, or generate AI-friendly schema context from DBX-managed databases. Do NOT use for write operations unless the user explicitly confirms with --allow-writes.