openinference AGENTS.md

Instructions for OpenInference, a monorepo containing related Python, JavaScript, and Java packages for recording AI and machine-learning application activity with OpenTelemetry. A monorepo is one repository that holds multiple projects.

In plain words
What is it for?
Use them when working on instrumentation packages, semantic conventions, examples, specifications, or language-specific build and test commands.
Why use it?
They explain the repository's language-specific areas and package layout so changes and commands are made in the right place.

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/arize-ai/openinference/agents-md
Clone the repo
git clone --depth 1 https://github.com/Arize-ai/openinference

Made for: Codex, OpenCode.

Per session 1,064 This file is loaded in full into every session.
When invoked 1,064 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 $0.01064 $0.01064
Opus 5 $0.00532 $0.00532
Sonnet 5 $0.00213 $0.00213
Haiku 4.5 $0.00106 $0.00106

Measured 2d ago against content hash 1d7143ee3f8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openinference 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 2d 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 · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working with this repository.

Repository Overview

OpenInference is a multi-language monorepo providing OpenTelemetry-based instrumentation for AI/ML applications:

  • Python: Instrumentation for OpenAI, LangChain, LlamaIndex, DSPy, etc.
  • JavaScript/TypeScript: Node.js instrumentations with pnpm workspaces
  • Java: Instrumentation for LangChain4j and Spring AI
  • Specification: OpenInference semantic conventions in spec/

Repository Structure

.
├── python/                    # Python packages and instrumentations
│   ├── instrumentation/       # Individual instrumentor packages
│   ├── openinference-instrumentation/
│   └── openinference-semantic-conventions/
├── js/                        # JavaScript/TypeScript workspace
│   ├── packages/              # pnpm workspace packages
│   └── examples/
├── java/                      # Java packages
│   ├── instrumentation/
│   ├── openinference-instrumentation/
│   └── openinference-semantic-conventions/
├── spec/                      # OpenInference specification
└── scripts/                   # Repository automation scripts

Essential Commands by Language

Python

Package Management:

# Install development dependencies
pip install -r python/dev-requirements.txt

# Install tox-uv for testing automation
pip install tox-uv==1.11.2

# Compose namespace package
tox run -e add_symlinks

# Install in editable mode
pip install -e python/openinference-instrumentation

Testing and Quality:

# Run all CI checks in parallel
tox run-parallel

# Run tests for specific package (e.g., openai)
tox run -e test-openai

# Run linting and formatting
tox run -e ruff-openai

# Run type checking
tox run -e mypy-openai

# Run all checks for a package
tox run -e ruff-mypy-test-openai

Key Tools:

  • tox for automation
  • ruff for formatting and linting
  • mypy for type checking

JavaScript/TypeScript

See js/CLAUDE.md for detailed JavaScript-specific guidance.

Read the full file on GitHub · 177 lines

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. 2d ago First seen · 177 lines · 1,064 tokens per session scan A 1d7143ee3f8c

Subscribe to this mod's changes

openinference AGENTS.md is an instructions file published in the GitHub repository Arize-ai/openinference (1,186 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,064 tokens to every session, about $0.0053 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.