metrics

metrics is a command for coding agents from gotempsh/temps. It costs 0 tokens per session (1,010 once invoked), scanned A, original, Apache-2.0.

A command-line tool for querying OpenTelemetry application metrics. OpenTelemetry is a common way for applications to record measurements such as request counts, durations, and error rates.

In plain words
What is it for?
Use it to find metric names, inspect label keys and values, and query metrics with time grouping and aggregation for a project.
Why use it?
It helps investigate application behaviour by showing available metrics, their labels, and values over selected time periods. It is for application measurements, not container or Docker resource statistics.

Command

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

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 metrics

README.md
[![agentmods](https://agentmods.dev/badge/commands/gotempsh/temps/metrics.svg)](https://agentmods.dev/commands/gotempsh/temps/metrics)
Your own site
<a href="https://agentmods.dev/commands/gotempsh/temps/metrics"><img src="https://agentmods.dev/badge/commands/gotempsh/temps/metrics.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 1,010 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 $0.01010
Opus 5 $0.00000 $0.00505
Sonnet 5 $0.00000 $0.00202
Haiku 4.5 $0.00000 $0.00101

Measured 2d ago against content hash 014cdd03d55f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

metrics 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/metrics.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

metrics command reference

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

metrics (alias: metric)

Query OTel application metrics for debugging (not container/docker stats — see "temps containers metrics" for those)

Subcommands:

  • names - List distinct metric names ingested for a project — start here if you don't know what to query
  • query - Query a metric with time bucketing and aggregation
  • label-keys - List the label keys observed on a metric — powers filter/group-by discovery
  • label-values - List the distinct values seen for a label key on a metric

metrics names

List distinct metric names ingested for a project — start here if you don't know what to query

Options:

Flag Description Default Required
-p, --project <project> Project slug or ID - No
--json Output in JSON format - No

metrics query

Query a metric with time bucketing and aggregation

Options:

Flag Description Default Required
-p, --project <project> Project slug or ID - No
--metric-name <name> Metric to query (see "temps metrics names") - No
--service-name <name> Filter by service name - No
--environment <name> Filter by deployment environment name - No
--period <period> Time period: today, h, d, m (e.g. 1h, 24h, 7d) 24h No
--start-time <iso> Explicit window start (RFC 3339) — overrides --period - No
--end-time <iso> Explicit window end (RFC 3339) — overrides --period - No
--bucket-interval <interval> Bucket size, e.g. "5 minutes", "1 hour" - No
--aggregation <mode> Per-bucket aggregation: avg (default), sum, min, max, count, rate, p50/p95/p99, quantile:0.95 - No
--metric-type <type> Filter by metric type: gauge, sum, histogram, exponential_histogram, summary - No
--label-filters <pairs> Comma-separated key=value data-point label filters, e.g. http.method=GET,http.status_code=200 - No
--group-by <keys> Comma-separated label keys to group series by, e.g. http.method,http.route - No
--limit <n> Max buckets to return (default: 500, server cap: 1000) - No
--json Output in JSON format - No

Read the full file on GitHub · 80 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 · 80 lines · 0 tokens per session scan A 014cdd03d55f

Subscribe to this mod's changes

metrics is a command published in the GitHub repository gotempsh/temps (712 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,010 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.