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/vercel/ai/agents-mdgit clone --depth 1 https://github.com/vercel/aiWhat 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 | $0.02900 | $0.02900 |
| Opus 5 | $0.01450 | $0.01450 |
| Sonnet 5 | $0.00580 | $0.00580 |
| Haiku 4.5 | $0.00290 | $0.00290 |
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.
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.
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 · 321 lines · 2,900 tokens per session scan A 8c2ff038ca15
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.
Other instructions, from other repositories
agent-starter-pack GEMINI.md
Instructions for GoogleCloudPlatform/agent-starter-pack, covering agent starter pack - ai coding agent guide, core principles for ai agents, project architecture overview, 4-layer template system and key directory structure.
langgraphjs CLAUDE.md
Instructions for langchain-ai/langgraphjs, covering langgraphjs development guide, corridor security analysis, build & test commands, code style guidelines and library architecture.
langgraphjs AGENTS.md
Instructions for langchain-ai/langgraphjs, covering repository instructions and corridor security analysis.
dafthunk CLAUDE.md
Instructions for dafthunk-com/dafthunk, covering claude.md, project overview, development commands, common commands and workspace-specific (use --filter).
GPTPortal AGENTS.md
Instructions for Zaki-1052/GPTPortal, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
google-ai-mcp AGENTS.md
Instructions for sandraschi/google-ai-mcp, covering google-ai-mcp — agent guide, entry points, quick ref, ports and architecture.