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 skills/arize-ai/openinference/phoenix-clinpx skills add Arize-ai/openinference --skill phoenix-cligit clone --depth 1 https://github.com/Arize-ai/openinferenceWhat 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 | $0.00113 | $0.03941 |
| Opus 5 | $0.00056 | $0.01971 |
| Sonnet 5 | $0.00023 | $0.00788 |
| Haiku 4.5 | $0.00011 | $0.00394 |
Grade A, and why
phoenix-cli 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.
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phoenix CLI
Invocation
px <resource> <action> # if installed globally
npx @arizeai/phoenix-cli <resource> <action> # no install required
The CLI uses singular resource commands with subcommands like list and get:
px trace list
px trace get <trace-id>
px trace annotate <trace-id>
px trace add-note <trace-id>
px trace-annotations delete
px span list
px span annotate <span-id>
px span add-note <span-id>
px span-annotations delete
px session list
px session get <session-id>
px session annotate <session-id>
px session add-note <session-id>
px session-annotations delete
px dataset list
px dataset get <name>
px project list
px project get <name>
px annotation-config list
px auth status
px profile list
px profile show [name]
px profile create <name>
px profile use <name>
px profile edit <name>
px profile delete <name>
Setup
export PHOENIX_HOST=http://localhost:6006
export PHOENIX_PROJECT=my-project
export PHOENIX_API_KEY=your-api-key # if auth is enabled
Always use --format raw --no-progress when piping to jq.
Quick Reference
| Task | Files |
|---|---|
| Look at sampled traces, spans, or sessions and write specific notes about what went wrong (no taxonomy yet) | references/open-coding |
| Group those notes into a structured failure taxonomy and quantify what matters | references/axial-coding |
Both stages tag every artifact with one shared coding annotation identifier (descriptive shape, e.g. coding-run:chatbot-context-loss-2026-05-06) so the run is queryable, reversible, and viewable as a unit. Pass --identifier <value> explicitly on every px call — shell inheritance is unreliable across agent harnesses. Open coding writes notes via px ... add-note and records a small local JSONL sidecar at .px/coding/<sanitized-identifier>.jsonl; axial coding reads that sidecar as the deterministic handoff and records labels in .px/coding/<sanitized-identifier>-axial.jsonl. Pick the identifier once per run (see references/open-coding.md), then share the Phoenix UI link from the wrap-up section. Revert is opt-in and runs three identifier-bound DELETEs only after explicit user confirmation.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 310 lines · 113 tokens per session scan A dde98a935bea
phoenix-cli is a skill published in the GitHub repository Arize-ai/openinference (1,186 stars, last pushed 2d ago), licensed Apache-2.0. It adds 113 tokens to every session and 3,941 once invoked, about $0.0006 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 skills, from other repositories
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.
frontmcp-observability
Use when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server. Covers zero-config OpenTelemetry distributed tracing across all flows; the this.telemetry API for custom spans, events, and attributes in tools, plugins, agents, and skills; structured JSON logging with trace correlation and…
opentelemetry-net-instrumentation
Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, logs, naming conventions, error handling, performance, SDK setup, resources, context propagation, and API design best practices.
golang-observability-opentelemetry
Instrumenting Go applications with OpenTelemetry for distributed tracing, Prometheus for metrics, and structured logging with slog.
debugging-with-wide-events
Use when investigating production behavior by querying wide events (a slow route, an error spike, a suspicious deploy, "why is this happening for account X"). Covers the data model, the symptom-to-query workflow, and standing queries worth running.
setting-up-wide-events-store
Use when a human asks to set up, deploy, or finish deploying the bundled Wide Events DuckDB store (the Kamal accessory that receives production telemetry). Covers the store generator, DNS, kamal setup, and post-deploy verification end to end.