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/clickhouse-go/agents-mdgit clone --depth 1 https://github.com/ClickHouse/clickhouse-goWhat 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 | $0.00008 | $0.00008 |
| Opus 5 | $0.00004 | $0.00004 |
| Sonnet 5 | $0.00002 | $0.00002 |
| Haiku 4.5 | $0.00001 | $0.00001 |
Grade A, and why
clickhouse-go 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 yesterday.
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
4 near-identical copies found in the catalogue:
- compass GEMINI.md — 100% identical, 2 lines differ
- tilt-mcp AGENTS.md — 100% identical, 0 lines differ
- pcl CLAUDE.md — 100% identical, 1 lines differ
- wren-engine AGENTS.md — 94% identical, 14 lines differ
What it actually says
.claude/CLAUDE.md
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.
- yesterday First seen · 1 lines · 8 tokens per session scan A 317ae893ef4a
clickhouse-go AGENTS.md is an instructions file published in the GitHub repository ClickHouse/clickhouse-go (3,335 stars, last pushed 3d ago), licensed Apache-2.0. It adds 8 tokens to every session, about $0.0000 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
jitsu AGENTS.md
Instructions for jitsucom/jitsu, covering jitsu — agent guidelines, project overview, repository structure, go (/bulker) and node.js / typescript.
sq AGENTS.md
Instructions for neilotoole/sq, covering agents.md, about sq, key documents, common commands and conventions.
sq CLAUDE.md
Instructions for neilotoole/sq: Claude Code entry point for this repo. Shared rules live in AGENTS.md.
jitsu CLAUDE.md
Instructions for jitsucom/jitsu, a project described as: Jitsu is an open-source Segment alternative. Fully-scriptable data ingestion engine for modern data teams. Set-up a real-time data pipeline in minutes, not days.
mcp-read-only-sql AGENTS.md
AGENTS.md instructions for lukleh/mcp-read-only-sql, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
mcp CLAUDE.md
Instructions for comcpwork/mcp, covering mcp 项目开发要求, 零、文档规范, 一、强制要求（must do）, 1. 成功证明要求 and 2. 命名规范.