lance-duckdb: Instructions file for Codex

AGENTS.md

lance-duckdb AGENTS.md is an instructions file for Codex, OpenCode from lance-format/lance-duckdb. It costs 1,967 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for a DuckDB extension that lets DuckDB query Lance datasets, including vector and full-text searches. DuckDB is a database for analytics, while Lance is a data format for machine-learning data.

In plain words
What is it for?
Use them when documenting, implementing, reviewing, testing, or changing compatibility in the lance-duckdb extension.
Why use it?
They explain which upstream DuckDB and Lance rules take priority and how the C++ and Rust parts must work together.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is lance-format/lance-duckdb's own configuration. It tells Codex and OpenCode how to work on lance-duckdb itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lance-duckdb configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lance-format/lance-duckdb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lance-format/lance-duckdb/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/lance-format/lance-duckdb

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for lance-duckdb AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lance-format/lance-duckdb/agents-md/github.svg)](https://agentmods.dev/instructions/lance-format/lance-duckdb/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lance-format/lance-duckdb/agents-md"><img src="https://agentmods.dev/badge/instructions/lance-format/lance-duckdb/agents-md/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.

agentmods 80×15 button for lance-duckdb AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lance-format/lance-duckdb/agents-md"><img src="https://agentmods.dev/badge/instructions/lance-format/lance-duckdb/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,967 This file is loaded in full into every session.
When invoked 1,967 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01967 $0.01967
Opus 5.5 $0.00787 $0.00787
Sonnet 5.5 $0.00393 $0.00393
Haiku 4.5 $0.00197 $0.00197

Measured 20d ago against content hash d6b91fab2148, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lance-duckdb 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 20d 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.

AGENTS.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Overview

This repository contains a DuckDB extension for querying Lance format datasets (including scan, vector search, and full-text search). The DuckDB integration is implemented in C++ (under src/) and links a Rust static library (lance_duckdb_ffi) that uses the Lance Rust crate and exports data via the Arrow C Data Interface.

Version and Release Policy

  • Lance is a DuckDB core extension. lance-duckdb has no independent product version or release cadence; delivery follows DuckDB releases and the target DuckDB commit.
  • Do not propose or create lance-duckdb version bumps, release tags, or GitHub releases. DuckDB owns official core-extension publication and selects this repository's latest main for the active target.
  • Identify compatibility by DuckDB release/commit and platform. Identify extension source by its lance-duckdb commit. Record both commits when reporting validation; repository CI success is distinct from official artifact availability.
  • The duckdb gitlink pins the tested upstream commit. DuckDB-named maintenance branches are compatibility lines, not independent extension versions. Keep gitlinks, branch annotations, and CI targets aligned when changing the DuckDB target.
  • Cargo package versions are internal metadata; Lance dependency versions and dataset/storage/IR versions are separate concepts. Preserve DuckDB's generated build metadata without treating it as an independent product version.
  • Follow DuckDB compatibility and release policy for branch and publication details.

Documentation Language

All documentation in this repository (including README.md and files under docs/) must be written in English.

Constraint Hierarchy (Highest Priority)

For any planning, implementation, review, or refactor work in this repository:

  • The only hard constraints are upstream DuckDB requirements and upstream Lance requirements.
  • If any repository-local guidance conflicts with DuckDB or Lance behavior/contracts, follow DuckDB/Lance.
  • Any decision made inside lance-duckdb (APIs/ABIs, FFI boundaries, internal formats, module boundaries, naming, testing conventions, or implementation strategies) is mutable and may be changed when a better design is found.
  • Treat repository-local rules in this document as default guidance, not immutable policy.

Read the full file on GitHub · 163 lines

Changes

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.

  1. 20d ago Changed · +9 lines · +231 tokens per session d6b91fab2148
  2. 21d ago Changed · +4 lines · +64 tokens per session 46ef21eb0ba0
  3. 2mo ago First seen · 150 lines · 1,672 tokens per session scan A e5c687fc3d5b

Subscribe to this mod's changes

lance-duckdb AGENTS.md is an instructions file published in the GitHub repository lance-format/lance-duckdb (136 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,967 tokens to every session, about $0.0079 per session on Opus 5.5. 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.

Related

lance-duckdb AGENTS.md compared with instructions from other repositories

lance-duckdb AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lance-duckdb AGENTS.mdlance-format/lance-duckdbInstructions file1362d agoApache-2.0A1,967Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode