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/orlando-japan/claude-code-setting/tracing-setupnpx skills add orlando-japan/claude-code-setting --skill tracing-setupgit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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.
[](https://agentmods.dev/skills/orlando-japan/claude-code-setting/tracing-setup)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/tracing-setup"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/tracing-setup.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00035 | $0.00843 |
| Opus 5 | $0.00017 | $0.00421 |
| Sonnet 5 | $0.00007 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
tracing-setup 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 4d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tracing setup
Metrics answer "is it slow?" Logs answer "what happened at this point?" Traces answer "where did my request spend its time?" — across services, async boundaries, and databases.
The model
A trace is a tree of spans. A span represents a unit of work: a request, a DB query, an external call. Each span has:
- A name ("http POST /orders")
- Start and end timestamps
- A parent span (or root)
- Key-value attributes (user_id, status code, query shape)
- Events and errors attached
The trace ID propagates across service boundaries (usually via a header: traceparent in W3C trace context).
Minimum viable tracing
- Pick a backend. Jaeger, Tempo, Honeycomb, Datadog, Lightstep. All support OpenTelemetry.
- Use OpenTelemetry. Vendor lock-in on tracing protocols is expensive to unwind. OTel is the standard.
- Auto-instrument what you can. Most HTTP servers, DB drivers, and HTTP clients have OTel auto-instrumentation that creates spans for free.
- Propagate trace context across service boundaries. The HTTP client and server both need to handle the
traceparentheader. - Sample. 100% sampling is too expensive in production. 1–10% head-based or tail-based sampling is typical.
What to span
- Incoming requests (auto).
- Outgoing HTTP calls (auto).
- DB queries (auto, via instrumented driver).
- Async work — jobs, background tasks (usually manual).
- Expensive computation (manual) — anything you want to see the duration of.
Don't span every function call. Traces get unreadable, storage gets expensive.
Span attributes
Attach context so you can filter traces later:
user_id(with PII rules — hash or omit if sensitive)request_idroute(the matched route, not the literal URL with IDs)db.statement(parameterized, not the raw query with values)error.kindon failed spans
Cardinality rules: same as metrics labels. Avoid per-request-unique values in attributes you'll want to aggregate.
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.
- 4d ago First seen · 79 lines · 35 tokens per session scan A a97c2245ddbc
tracing-setup is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 843 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
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.
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…
observability
Use when instrumenting a service from the inside so an incident can be explained from telemetry alone — wiring OpenTelemetry logs, metrics and traces, standing up a Collector, exporting via OTLP, and defining telemetry-driven alerts. NOT outside-in uptime probes, on-call rotation, or who-gets-paged (that is…
golang-observability-opentelemetry
Instrumenting Go applications with OpenTelemetry for distributed tracing, Prometheus for metrics, and structured logging with slog.
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.