transformers AGENTS.md

Project-specific instructions for Hugging Face Transformers, a software library for running and training machine-learning models that work with text, images, audio, and other data.

In plain words
What is it for?
Use it when working in the Hugging Face Transformers project, especially files covered by .ai/AGENTS.md.
Why use it?
It helps the agent follow the repository's local rules when changing Transformers 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/huggingface/transformers/agents-md
Clone the repo
git clone --depth 1 https://github.com/huggingface/transformers

Made for: Codex, OpenCode.

Per session 5 This file is loaded in full into every session.
When invoked 5 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00005 $0.00005
Opus 5 $0.00003 $0.00003
Sonnet 5 $0.00001 $0.00001
Haiku 4.5 $0.00001 $0.00001

Measured yesterday against content hash 13285a5fd29e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

transformers 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.

Origin

Copies of this mod

4 near-identical copies found in the catalogue:

AGENTS.md · 1 lines

What it actually says

.ai/AGENTS.md

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 · 1 lines · 5 tokens per session scan A 13285a5fd29e

Subscribe to this mod's changes

transformers AGENTS.md is an instructions file published in the GitHub repository huggingface/transformers (164,637 stars, last pushed yesterday), licensed Apache-2.0. It adds 5 tokens to every session, about $0.0000 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.