litellm AGENTS.md

Project instructions for LiteLLM, an AI gateway that connects applications to many language-model services through common interfaces. The project includes a Rust core and a Python SDK.

In plain words
What is it for?
Following project instructions when changing, reviewing, or testing the LiteLLM codebase.
Why use it?
They give a coding agent repository-specific guidance while working on LiteLLM's model connections, cost tracking, safeguards, traffic distribution, or logging.

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/berriai/litellm/agents-md
Clone the repo
git clone --depth 1 https://github.com/BerriAI/litellm

Made for: Codex, OpenCode.

Per session 10 This file is loaded in full into every session.
When invoked 10 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 $0.00010 $0.00010
Opus 5 $0.00005 $0.00005
Sonnet 5 $0.00002 $0.00002
Haiku 4.5 $0.00001 $0.00001

Measured 3d ago against content hash 7b3d9a1a5e3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

litellm 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 3d 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.

AGENTS.md · 2 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. 3d ago First seen · 2 lines · 10 tokens per session scan A 7b3d9a1a5e3c

Subscribe to this mod's changes

litellm AGENTS.md is an instructions file published in the GitHub repository BerriAI/litellm (57,772 stars, last pushed yesterday), with no licence file. It adds 10 tokens to every session, about $0.0001 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.