ai AGENTS.md

Project instructions stored in an `AGENTS.md` file for the Vercel AI SDK codebase, a TypeScript library for building AI applications and agents.

In plain words
What is it for?
Use them when working on the Vercel AI SDK repository and its agent instructions.
Why use it?
They give coding agents background about the project, its layout, and the locations and dependencies they need to understand before changing code.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/vercel/ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/vercel/ai

Made for: Codex, OpenCode.

Per session 2,900 This file is loaded in full into every session.
When invoked 2,900 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.02900 $0.02900
Opus 5 $0.01450 $0.01450
Sonnet 5 $0.00580 $0.00580
Haiku 4.5 $0.00290 $0.00290

Measured yesterday against content hash 8c2ff038ca15, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai 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.

AGENTS.md · 321 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. yesterday First seen · 321 lines · 2,900 tokens per session scan A 8c2ff038ca15

Subscribe to this mod's changes

ai AGENTS.md is an instructions file published in the GitHub repository vercel/ai (26,510 stars, last pushed today), with no licence file. It adds 2,900 tokens to every session, about $0.0145 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.