clickhouse-go is a Go client and driver for ClickHouse, a database designed for analytical data workloads. It lets Go programs connect to ClickHouse over its native TCP or HTTP protocols, run queries, and read or write data through native or standard database interfaces. Catalogue add-ons provide agent instructions and skills for using the driver.
Borrowing it
Nothing to install: this file belongs to ClickHouse/clickhouse-go. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ClickHouse/clickhouse-go/main/.claude/skills/review-pr/SKILL.mdgit clone --depth 1 https://github.com/ClickHouse/clickhouse-goWrote 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/clickhouse-go/review-pr)<a href="https://agentmods.dev/skills/clickhouse/clickhouse-go/review-pr"><img src="https://agentmods.dev/badge/skills/clickhouse/clickhouse-go/review-pr/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/clickhouse-go/review-pr"><img src="https://agentmods.dev/badge/skills/clickhouse/clickhouse-go/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00071 | $0.02266 |
| Opus 5 | $0.00036 | $0.01133 |
| Sonnet 5 | $0.00014 | $0.00453 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade A, and why
review-pr 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 10d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
clickhouse-go PR Review Skill
Reviews an open GitHub pull request and posts the findings. The review criteria — the review
gates, the clickhouse-go supporting checks, and the severity model — are defined in
@.claude/skills/review-pr/review-core.md. When this skill is invoked as /review-pr from the
repo root, that reference injects the file into context automatically; if the core content is
not already in your context (e.g. you were pointed at this file directly), Read that path
before reviewing. Apply it in full — this file adds only the GitHub plumbing: fetching the PR,
the findings JSON schema, and posting.
Reviewing a local diff with no PR (e.g. before opening one)? Use review-core.md directly and
report findings as plain text — none of the JSON/posting machinery below applies.
Arguments
$0(required): PR number (e.g.1869).
1. Obtain the diff and context
gh pr view "$0" --json title,body,headRefName,baseRefName,author,url
gh pr diff "$0"
- Read the title, description, and any linked issues for the intended behavior.
- For each changed file,
Readthe surrounding code when the diff alone is insufficient to judge the change — a finding is only valid if you understand the code it touches. - If the diff is large (>2000 lines), use the
Exploreagent to analyze parts in parallel.
Existing review threads (re-review)
If existing-threads.json is present (the CI workflow writes it; create it for interactive runs
with python3 .claude/skills/review-pr/post_review.py fetch --repo ClickHouse/clickhouse-go --pr "$0" > existing-threads.json),
Read it. It lists the review threads you already started, each with its prior comment(s), any
author replies, and is_resolved/is_outdated state. For every open (is_resolved: false)
thread, decide an action (section 3, thread_actions):
- The author replied with a question or pushback that still stands → reply addressing it.
- The concern is now addressed (the current code satisfies it, or the author's reply adequately resolves/declines it) → resolve (optionally with a short closing reply).
- The concern still stands and there is no new author activity → keep (no new comment).
- The thread is
is_outdatedand the underlying concern no longer applies → resolve.
What ships with it
2 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.
- 10d ago First seen · 183 lines · 71 tokens per session scan A 1b6212a40a8e
review-pr is a skill published in the GitHub repository ClickHouse/clickhouse-go (3,343 stars, last pushed yesterday), licensed Apache-2.0. It adds 71 tokens to every session and 2,266 once invoked, about $0.0004 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
sq
Guides use of the sq CLI to query SQL databases and tabular files with SLQ (sq's jq-like query language) or native SQL, manage sources, choose output formats, and run inspect, diff, and table commands. Use when the user mentions sq, SLQ, wrangling CSV/Excel/JSON/DB data, cross-source joins, or command-line data…
clickhouse-analytics
Use when running a ClickHouse server for high-volume OLAP: choosing a MergeTree engine and ORDER BY/PARTITION BY keys, ingesting billions of event/log/metric rows, pre-aggregating with materialized views, or fixing a query that scans instead of pruning. NOT in-process file analytics (that is duckdb), NOT OLTP CRUD…
huawei-cloud-mrs-clickhouse-sql-check
Comprehensive SQL statement checking for ClickHouse, supporting multiple kernel versions (24.8, 23.3, 22.3) and two check modes: 1. Syntax Check - Keyword validation, statement structure verification, clause completeness, ClickHouse-specific syntax compatibility (SAMPLE BY, FINAL, ARRAY JOIN, PREWHERE, GLOBAL JOIN…
golang-database-patterns
Go database integration patterns using sqlx, pgx, and migration tools like golang-migrate.
relational-database-design
Designs or reviews a relational database schema for a given domain. Covers table structure, normalization, indexes, constraints, and migration strategy. Invoked when the user asks to design a schema, review a database structure, or optimize a data model.
SQL Query Optimizer
Reviews SQL queries for performance issues and rewrites them with optimized execution plans.