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 agentmods add skills/clickhouse/clickhouse-claude-code-plugin/setupnpx skills add ClickHouse/clickhouse-claude-code-plugin --skill setupgit clone --depth 1 https://github.com/ClickHouse/clickhouse-claude-code-pluginWhat 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 | $0.00035 | $0.00761 |
| Opus 5 | $0.00017 | $0.00380 |
| Sonnet 5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
setup 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 2d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClickHouse Plugin Setup
This plugin includes the ClickHouse Cloud Remote MCP server at https://mcp.clickhouse.cloud/mcp. It provides secure, read-only access to your ClickHouse Cloud clusters.
Setup Steps
-
Verify the MCP server is connected: Check that the ClickHouse MCP server appears in your available tools. If it does, you're ready to go.
-
Authenticate via OAuth: The MCP server uses OAuth with your ClickHouse Cloud credentials. Follow the prompts when first connecting to authorize access.
-
Test the connection: Try listing databases or running a simple SELECT query to confirm everything works.
Troubleshooting
- Server not appearing: Run
/reload-pluginsto reload plugin MCP servers. - Authentication errors: Re-authenticate by following the OAuth flow when prompted.
- Connection timeouts: Verify your network can reach
https://mcp.clickhouse.cloud. The MCP server is a remote HTTP endpoint and requires internet access.
Claude Code Timeout Limitation
Claude Code enforces a 30-second timeout on all MCP tool calls. This cannot be changed by the user or the MCP server. While the run_select_query tool accepts a timeoutSeconds parameter (default 300s, max 3600s), Claude Code will kill the connection after 30 seconds regardless of this setting.
Implications:
- Keep queries simple and fast — complex analytical queries that take longer than 30 seconds will fail
- Use
LIMITclauses to bound result sets - Prefer querying materialized views or pre-aggregated tables over raw scans of large tables
- If a query times out, break it into smaller, faster queries rather than increasing
timeoutSeconds
What the MCP Server Provides
Once connected, the ClickHouse MCP server provides these tools:
Organization & Service Management
- get_organizations — list all accessible ClickHouse Cloud organizations
- get_organization_details — details of a single organization
- get_services_list — list all services in an organization
- get_service_details — details of a single service
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.
- 2d ago First seen · 67 lines · 35 tokens per session scan A 1005b8a72fb2
setup is a skill published in the GitHub repository ClickHouse/clickhouse-claude-code-plugin (6 stars, last pushed 23d ago), licensed Apache-2.0. It adds 35 tokens to every session and 761 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.