Borrowing it
Nothing to install: this file belongs to txn2/mcp-trino. 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/txn2/mcp-trino/main/CLAUDE.mdgit clone --depth 1 https://github.com/txn2/mcp-trinoWrote 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/txn2/mcp-trino/claude-md)<a href="https://agentmods.dev/instructions/txn2/mcp-trino/claude-md"><img src="https://agentmods.dev/badge/instructions/txn2/mcp-trino/claude-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 5.1 | $0.03255 | $0.03255 |
| Opus 5 | $0.01628 | $0.01628 |
| Sonnet 5 | $0.00651 | $0.00651 |
| Haiku 4.5 | $0.00326 | $0.00326 |
Grade A, and why
mcp-trino CLAUDE.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 7d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code when working with this project.
Project Overview
mcp-trino is a generic, open-source MCP (Model Context Protocol) server for Trino. It enables AI assistants to query and explore data warehouses via the MCP protocol.
Key Design Goals:
- Composable: Can be used standalone OR imported as a library
- Generic: No domain-specific logic; suitable for any Trino deployment
- Secure: Configurable limits and timeouts to prevent abuse
CRITICAL - Factual Integrity (No Confabulation)
AI-generated prose (PR descriptions, commit messages, reviews, explanations) is held to the same verification standard as code. Unverified claims are as unacceptable as untested code.
-
Never assert facts you haven't verified. Before stating that a file contains X, a config is missing Y, or a system behaves in way Z — READ the file, CHECK the config, VERIFY the behavior. If you haven't looked, say "I haven't verified this" or say nothing.
-
Every claim must be evidence-linked. PR descriptions, commit messages, and work summaries may only include claims that are either: (a) directly visible in the diff, or (b) verified by reading a specific file (cite file:line). No exceptions.
-
Never pad or embellish. If you made two fixes, describe two fixes. Do not invent a third to make the work look more complete. Do not present hypotheses as confirmed diagnoses.
-
Uncertainty must be explicit. Use "I believe," "possibly," or "I haven't verified" when uncertain. Never upgrade a guess to a fact.
-
When reviewing, verify claims against evidence. Treat PR descriptions and commit messages as claims to be fact-checked, not trusted context.
-
Omission over fabrication. A gap stated honestly is better than a fabricated answer stated confidently. When in doubt, leave it out.
Order of Work (AI contributions)
Every change follows this order. make verify is the LAST step before handing work to the human — not the first, and not a substitute for review.
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.
- 7d ago First seen · 206 lines · 3,255 tokens per session scan A 9ea2e2af18ce
mcp-trino CLAUDE.md is an instructions file published in the GitHub repository txn2/mcp-trino (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,255 tokens to every session, about $0.0163 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.