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 instructions/clickhouse/agent-skills/agents-mdgit 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/instructions/clickhouse/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/clickhouse/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/clickhouse/agent-skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01897 | $0.01897 |
| Opus 5 | $0.00949 | $0.00949 |
| Sonnet 5 | $0.00379 | $0.00379 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
agent-skills AGENTS.md 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 4d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, etc.) when working with code in this repository.
Repository Overview
A collection of skills for AI agents working with ClickHouse databases and chdb (in-process ClickHouse for Python). Skills are packaged instructions and guidelines that extend agent capabilities for database design, query optimization, operational best practices, and in-process data analytics.
Repository Structure
agent-skills/
├── skills/
│ ├── clickhouse-best-practices/ # ClickHouse optimization guidelines
│ │ ├── SKILL.md # Skill definition (overview)
│ │ ├── AGENTS.md # Full compiled guide (generated)
│ │ ├── metadata.json # Version, organization, abstract
│ │ ├── README.md # Maintainer guide
│ │ └── rules/ # Individual rule files
│ │ ├── _sections.md # Section metadata
│ │ ├── _template.md # Template for new rules
│ │ └── *.md # Rule files (e.g., query-use-prewhere.md)
│ ├── chdb-datastore/ # chdb pandas-compatible DataStore API
│ │ ├── SKILL.md # Skill definition and quick-start
│ │ ├── metadata.json # Version, organization, abstract
│ │ ├── README.md # Maintainer guide
│ │ ├── references/ # API reference docs
│ │ │ ├── api-reference.md # DataStore method signatures
│ │ │ └── connectors.md # All data source connection methods
│ │ ├── examples/
│ │ │ └── examples.md # Runnable examples
│ │ └── scripts/
│ │ └── verify_install.py # Environment verification
│ └── chdb-sql/ # chdb SQL API
│ ├── SKILL.md # Skill definition and quick-start
│ ├── metadata.json # Version, organization, abstract
│ ├── README.md # Maintainer guide
│ ├── references/ # SQL reference docs
│ │ ├── api-reference.md # query/Session/connect signatures
│ │ ├── table-functions.md # ClickHouse table functions
│ │ └── sql-functions.md # Commonly used SQL functions
│ ├── examples/
│ │ └── examples.md # Runnable examples
│ └── scripts/
│ └── verify_install.py # Environment verification
├── packages/
│ └── clickhouse-best-practices-build/ # Build tooling
│ ├── package.json # Bun scripts
│ ├── tsconfig.json # TypeScript config
│ └── src/
│ ├── config.ts # Path configuration
│ ├── types.ts # Type definitions
│ ├── parser.ts # Markdown parser
│ ├── build.ts # Build script
│ ├── validate.ts # Rule validator
│ ├── validate-sql.ts # SQL syntax validator
│ └── check-links.ts # Internal link checker
└── .github/
└── workflows/
└── clickhouse-best-practices-ci.yml # CI workflow
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.
- 4d ago First seen · 212 lines · 1,897 tokens per session scan A 676acaaebfb6
agent-skills AGENTS.md is an instructions file published in the GitHub repository ClickHouse/agent-skills (528 stars, last pushed 28d ago), licensed Apache-2.0. It adds 1,897 tokens to every session, about $0.0095 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 instructions, from other repositories
Addax AGENTS.md
AGENTS.md instructions for wgzhao/Addax, covering agents.md, 概述, 通用偏好, 编译 and 整体编译.
dory AGENTS.md
AGENTS.md instructions for dorylab/dory, covering agents.md, product model, core source areas, commands and coding rules.
dory CLAUDE.md
Claude Code instructions for dorylab/dory, covering dory - claude code guidelines, project structure, package manager, shadcn/ui and dependency upgrades.
phpClickHouse CLAUDE.md
Instructions for smi2/phpClickHouse, covering claude.md — phpclickhouse, project overview, principles, architecture and key notes.
qwery-core AGENTS.md
Instructions for Guepard-Corp/qwery-core, covering agents.md — strict rules for ai contributors, 1. non-negotiable invariants, 2. code quality rules, 3. hexagonal layout (target after restructure) and use cases (adr #33).
clickadvisor AGENTS.md
AGENTS.md instructions for olyannaa/clickadvisor, covering правила работы агентов с репозиторием, базовый принцип, перед изменениями, правила каталога and тесты и benchmark.