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 huaweicloud/huaweicloud-skills --skill huawei-cloud-mrs-clickhouse-sql-checkgit clone --depth 1 https://github.com/huaweicloud/huaweicloud-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/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-clickhouse-sql-check)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-clickhouse-sql-check"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-clickhouse-sql-check/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/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-clickhouse-sql-check"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-clickhouse-sql-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 33 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 101 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 66 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 126 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- low Excessive Agency · line 211 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00277 | $0.05549 |
| Opus 5 | $0.00138 | $0.02774 |
| Sonnet 5 | $0.00055 | $0.01110 |
| Haiku 4.5 | $0.00028 | $0.00555 |
Grade A, and why
huawei-cloud-mrs-clickhouse-sql-check 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.
How it starts
The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClickHouse SQL Check Skill
You are a ClickHouse SQL specification checking expert, responsible for comprehensive SQL statement checking for ClickHouse. You have a custom-built ClickHouse SQL tokenizer and statement recognizer that can precisely identify ClickHouse-specific syntax.
1. Overview
Architecture: This skill uses a three-stage pipeline: Tokenizer (lexical analysis) → Parser (statement recognition + syntax analysis) → Rule Engine (syntax + spec checking) → Report Generation.
Multi-Version Support: Version-specific grammar rules (keywords, grammar, token types)
are stored in rules/v{version}/ directories. Common development-spec rules are in
rules/common/. When a user invokes the skill, ask which ClickHouse kernel version
to use once per session (see Workflow below). Within the same session, reuse the
previously selected version and mode without asking again.
Supported Versions:
| Version | Keywords | Token Types | Statement Types | Source |
|---|---|---|---|---|
| 24.8 | 571 | 52 | 47 | CommonParsers.h APPLY_FOR_PARSER_KEYWORDS macro |
| 23.3 | 462 | 49 | 47 | Parser*.cpp ParserKeyword("...") calls (scattered) |
| 22.3 | 422 | 48 | 46 | Parser*.cpp ParserKeyword("...") calls (scattered) |
Source: All keywords and grammar rules are extracted directly from the
ClickHouse kernel source (src/Parsers/CommonParsers.h, src/Parsers/Lexer.h,
and src/Parsers/Parser*.cpp), ensuring accuracy and completeness.
Check Modes:
| Mode | Dependency | Description |
|---|---|---|
| syntax | None | Syntax check: keyword validity, statement structure, clause completeness, ClickHouse syntax compatibility |
| spec | None | Specification check: 35 development-spec rules (SPEC001-SPEC035) from MRS dev standards |
| all | None | Execute both syntax and specification checks |
Default: syntax mode. Use spec or all to enable specification rules.
Applicable Scenarios:
- Validate SQL syntax before executing on ClickHouse cluster
- Check ClickHouse-specific syntax (ENGINE, ORDER BY, PARTITION BY, SAMPLE BY, TTL, ARRAY JOIN, PREWHERE, GLOBAL JOIN, ASOF JOIN, FINAL, etc.)
- Identify potential syntax errors in SQL statements
- Review SQL for ClickHouse version-specific compatibility
What ships with it
19 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.
- references/ddl_grammar.md 15 KB
- references/dml_misc_grammar.md 13 KB
- references/select_grammar.md 9.8 KB
- references/token_types.md 5.7 KB
- rules/common/spec_rules.py 8.7 KB runs code
- rules/v22.3/grammar_rules.py 30 KB runs code
- rules/v22.3/keywords.py 21 KB runs code
- rules/v22.3/token_types.py 4.9 KB runs code
- rules/v23.3/grammar_rules.py 22 KB runs code
- rules/v23.3/keywords.py 23 KB runs code
- rules/v23.3/token_types.py 5.0 KB runs code
- rules/v24.8/grammar_rules.py 19 KB runs code
- rules/v24.8/keywords.py 23 KB runs code
- rules/v24.8/token_types.py 5.0 KB runs code
- scripts/ck_sql_checker.py 38 KB runs code
- scripts/ck_sql_parser.py 17 KB runs code
- scripts/ck_sql_tokenizer.py 16 KB runs code
- scripts/version_loader.py 3.2 KB runs code
- templates/report_template.md 865 B
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 · 463 lines · 277 tokens per session scan A caf457eb49b9
huawei-cloud-mrs-clickhouse-sql-check is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 277 tokens to every session and 5,549 once invoked, about $0.0014 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
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…
clickhouse
Design ClickHouse MergeTree tables, partitioning, and projections; inspect ingestion and analytical query performance.
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.
graphjin-eval
Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.
chdb-datastore
Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas. Provides chDB DataStore — same pandas API, ClickHouse engine underneath. Also handles reading from S3, MySQL, PostgreSQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake…