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/lance-format/lance-duckdb/agents-mdgit clone --depth 1 https://github.com/lance-format/lance-duckdbWhat 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 | $0.01672 | $0.01672 |
| Opus 5 | $0.00836 | $0.00836 |
| Sonnet 5 | $0.00334 | $0.00334 |
| Haiku 4.5 | $0.00167 | $0.00167 |
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 2d 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 — 150 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.
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.
Deliverable & Compatibility Policy
This project is delivered as a fully self-contained DuckDB extension artifact (statically linked in our distribution). Low-level APIs/ABIs/formats in this repository (C++/Rust FFI boundaries, internal encodings, file/IPC formats, etc.) are strictly internal implementation details:
- They are not intended to be directly consumed by end users.
- There are no external downstream users that depend on them.
- Prioritize first principles and the most direct correct design; do not optimize for migrations or compatibility unless explicitly requested.
- Compatibility commitments are driven by DuckDB/Lance behavior, not by historical repository-local decisions.
- User-facing contracts should be defined at the SQL surface.
Public Surface Policy (SQL-First)
Expose user-facing capabilities primarily through SQL, not internal helper functions.
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.
- 2d ago First seen · 150 lines · 1,672 tokens per session scan A e5c687fc3d5b
lance-duckdb AGENTS.md is an instructions file published in the GitHub repository lance-format/lance-duckdb (125 stars, last pushed 25d ago), licensed Apache-2.0. It adds 1,672 tokens to every session, about $0.0084 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
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.