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/huggingface/transformers/agents-mdgit clone --depth 1 https://github.com/huggingface/transformersWhat 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 | $0.00005 | $0.00005 |
| Opus 5 | $0.00003 | $0.00003 |
| Sonnet 5 | $0.00001 | $0.00001 |
| Haiku 4.5 | $0.00001 | $0.00001 |
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.
Copies of this mod
4 near-identical copies found in the catalogue:
- diffusers AGENTS.md — 100% identical, 0 lines differ
- transformers CLAUDE.md — 100% identical, 0 lines differ
- diffusers CLAUDE.md — 100% identical, 0 lines differ
- airig AGENTS.md — 100% identical, 0 lines differ
What it actually says
.ai/AGENTS.md
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 · 1 lines · 5 tokens per session scan A 13285a5fd29e
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.
Other instructions, from other repositories
huggingface_hub AGENTS.md
Instructions for huggingface/huggingface_hub, covering agent guide for huggingfacehub, project overview, setup, key commands and code structure.
huggingface_hub CLAUDE.md
Instructions for huggingface/huggingface_hub, a project described as: The official CLI and Python client for the Hugging Face Hub.
Kokoro-FastAPI AGENTS.md
Instructions for remsky/Kokoro-FastAPI, covering agents.md, layout, commands, conventions and gotchas.
piper-plus CLAUDE.md
Instructions for ayutaz/piper-plus, covering piper tts - プロジェクト概要, 📦 アーカイブ: zero-shot v7 学習成果 (feat/zero-shot-tts), 学習中の安定動作のために実装した 5 つの修正 (重要), リベース後のアーキテクチャ (v7 学習で実証済み) and v7 学習・評価実績 (v100 × 4、32 epoch 完走で停止).
diffusers AGENTS.md
Instructions for huggingface/diffusers, a project described as: 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
diffusers CLAUDE.md
Instructions for huggingface/diffusers, a project described as: 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.