traces

traces is a command for Claude Code from gotempsh/temps. It costs 0 tokens per session (629 once invoked), scanned A, original, Apache-2.0.

A command-line tool for inspecting distributed traces, which record how a request moves through multiple services. It ranks operations by time, latency percentiles, or inconsistency.

In plain words
What is it for?
Analyze trace spans over a time window and filter results by project, service, operation, name, or operation type.
Why use it?
It helps reveal which service operation is slow or behaving differently when performance problems cross service boundaries.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

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 commands/gotempsh/temps/traces
Clone the repo
git clone --depth 1 https://github.com/gotempsh/temps

Made for: Claude Code.

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.

agentmods badge for traces

README.md
[![agentmods](https://agentmods.dev/badge/commands/gotempsh/temps/traces.svg)](https://agentmods.dev/commands/gotempsh/temps/traces)
Your own site
<a href="https://agentmods.dev/commands/gotempsh/temps/traces"><img src="https://agentmods.dev/badge/commands/gotempsh/temps/traces.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 629 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00000 $0.00629
Opus 5 $0.00000 $0.00315
Sonnet 5 $0.00000 $0.00126
Haiku 4.5 $0.00000 $0.00063

Measured 2d ago against content hash 8cd607c82921, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

traces 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.

skills/temps/references/commands/traces.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

traces command reference

Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.

traces (alias: trace)

Inspect distributed traces and operation latency

Subcommands:

  • span-stats (operations, ops) - Rank operations by time spent, latency percentiles, or inconsistency

traces span-stats (alias: operations, ops)

Rank operations by time spent, latency percentiles, or inconsistency

Options:

Flag Description Default Required
--project-id <id> Project ID - No
--project-ids <ids> Comma-separated project IDs to rank across, e.g. 4,5,6 (max 50) - No
--since <duration> Relative window: 30m, 24h, 7d (max 31d) 24h No
--start-time <iso> Window start (ISO 8601); overrides --since - No
--end-time <iso> Window end (ISO 8601); defaults to now - No
--service <name> Only this service - No
--operation <name> Only this operation (exact span name) - No
--search <text> Only operations whose name contains this text - No
--kind <kind> Span kind (server, client, internal, producer, consumer, unspecified) - No
--status <status> Span status (ok, error, unset) - No
--environment-id <id> Only this environment - No
--deployment-id <id> Only this deployment - No
--attributes <pairs> Span attribute filters, e.g. db.system=postgresql - No
--min-duration-ms <ms> Ignore spans faster than this - No
--min-count <n> Drop operations with fewer samples than this - No
--sort-by <field> Ranking (total_time, p50, p95, p99, max, avg, stddev, count, errors, error_rate, variability, tail_ratio) total_time No
--sort-order <order> asc or desc desc No
--limit <n> Rows to show (max 100) 20 No
--offset <n> Page offset - No
--json Output in JSON format - No

Read the full file on GitHub · 43 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 · 43 lines · 0 tokens per session scan A 8cd607c82921

Subscribe to this mod's changes

traces is a command published in the GitHub repository gotempsh/temps (712 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 629 tokens. 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 2026-09-03.