What is setup-claude-code-tracing?

A setup guide for recording Claude Code or Agent SDK activity in Arize AX, a cloud service, or Phoenix, a self-hosted monitoring service.

It is for setting up tracing, creating an Arize project, getting an API key, configuring Claude Code or Agent SDK applications, and troubleshooting tracing.

It guides you through choosing a service, configuring credentials, enabling tracing, and fixing setup problems.

setup-claude-code-tracing — Skill for Claude Code by Arize-ai

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.

Any agent

npx skills add Arize-ai/arize-claude-code-plugin --skill setup-claude-code-tracing

Clone the repo

git clone --depth 1 https://github.com/Arize-ai/arize-claude-code-plugin

Made for: Claude Code.

Or install claude-code-tracing, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/arize-ai/arize-claude-code-plugin/setup-claude-code-tracing/github.svg)](https://agentmods.dev/skills/arize-ai/arize-claude-code-plugin/setup-claude-code-tracing)

Your own site

<a href="https://agentmods.dev/skills/arize-ai/arize-claude-code-plugin/setup-claude-code-tracing"><img src="https://agentmods.dev/badge/skills/arize-ai/arize-claude-code-plugin/setup-claude-code-tracing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/arize-ai/arize-claude-code-plugin/setup-claude-code-tracing"><img src="https://agentmods.dev/badge/skills/arize-ai/arize-claude-code-plugin/setup-claude-code-tracing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,219 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00130	$0.03219
Opus 5.5	$0.00052	$0.01288
Sonnet 5.5	$0.00026	$0.00644
Haiku 4.5	$0.00013	$0.00322

Measured 2mo ago against content hash 87ca2b54748e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

setup-claude-code-tracing scanned grade B with 2 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Globally** → `~/.claude/settings.json` (applies to all projects)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sf http://localhost:6006/v1/traces >/dev/null && echo "Phoenix is running" || echo "Phoenix not reachable"

plugins/claude-code-tracing/skills/setup-claude-code-tracing/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup Tracing

Configure OpenInference tracing for Claude Code sessions or Agent SDK applications to Arize AX (cloud) or Phoenix (self-hosted).

How to Use This Skill

This skill follows a decision tree workflow. Start by asking the user where they are in the setup process:

Are they using the Claude Code CLI or the Agent SDK?
- CLI → Continue to step 2
- Agent SDK (Python or TypeScript) → Go to Agent SDK Setup
Do they already have credentials?
- Yes → Jump to Configure Settings
- No → Continue to step 3
Which backend do they want to use?
- Phoenix (self-hosted) → Go to Set Up Phoenix
- Arize AX (cloud) → Go to Set Up Arize AX
Are they troubleshooting?
- Yes → Jump to Troubleshoot

Important: Only follow the relevant path for the user's needs. Don't go through all sections.

Set Up Phoenix

Phoenix is self-hosted and requires no Python dependencies for tracing.

Install Phoenix

Ask if they already have Phoenix running. If not, walk through:

# Option A: pip
pip install arize-phoenix && phoenix serve

# Option B: Docker
docker run -p 6006:6006 arizephoenix/phoenix:latest

Phoenix UI will be available at http://localhost:6006. Confirm it's running:

curl -sf http://localhost:6006/v1/traces >/dev/null && echo "Phoenix is running" || echo "Phoenix not reachable"

Then proceed to Configure Local Project with PHOENIX_ENDPOINT=http://localhost:6006.

Set Up Arize AX

Arize AX is available as a SaaS platform or as an on-prem deployment. Users need an account, a space, and an API key.

First, ask the user: "Are you using the Arize SaaS platform or an on-prem instance?"

SaaS → Uses the default endpoint (otlp.arize.com:443). Continue below.
On-prem → The user will need to provide their custom OTLP endpoint (e.g., otlp.mycompany.arize.com:443). Ask for it and note it for the Configure Settings step where it will be set as ARIZE_OTLP_ENDPOINT.

Read the full file on GitHub · 316 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.

2mo ago First seen · 316 lines · 130 tokens per session scan B 87ca2b54748e

Subscribe to this mod's changes

setup-claude-code-tracing is a skill published in the GitHub repository Arize-ai/arize-claude-code-plugin (25 stars, last pushed 3mo ago), licensed MIT. It adds 130 tokens to every session and 3,219 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics

setup-claude-code-tracing next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
setup-claude-code-tracingArize-ai/arize-claude-code-plugin	Skill	25	3mo ago	MIT	B	130	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

setup-claude-code-tracing