analyze-prometheus

analyze-prometheus is a command for Claude Code from evangelosmeklis/thufir. It costs 15 tokens per session (1,552 once invoked), scanned A, original, MIT.

A command for investigating why a Prometheus monitoring alert fired. Prometheus is a system that records measurements from software and raises alerts when they cross defined conditions.

In plain words
What is it for?
Use it for root-cause analysis of service incidents, including checking the alert expression, affected service, metrics, relevant code, and past commits.
Why use it?
It brings alert details, related measurements, source code, and code-change history together so the likely cause can be traced instead of guessed.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the thufir plugin — 4 skills, 4 commands, 3 MCP servers shipped together

Good fit Use it for root-cause analysis of service incidents, including checking the alert expression, affected service, metrics, relevant code, and past commits.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/evangelosmeklis/thufir/analyze-prometheus
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.

Clone the repo
git clone --depth 1 https://github.com/evangelosmeklis/thufir

Made for: Claude Code.

Or install thufir, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 3 MCP servers.

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 analyze-prometheus

README.md
[![agentmods](https://agentmods.dev/badge/commands/evangelosmeklis/thufir/analyze-prometheus/github.svg)](https://agentmods.dev/commands/evangelosmeklis/thufir/analyze-prometheus)
Your own site
<a href="https://agentmods.dev/commands/evangelosmeklis/thufir/analyze-prometheus"><img src="https://agentmods.dev/badge/commands/evangelosmeklis/thufir/analyze-prometheus/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.

agentmods 80×15 button for analyze-prometheus

Your own site · 80×15
<a href="https://agentmods.dev/commands/evangelosmeklis/thufir/analyze-prometheus"><img src="https://agentmods.dev/badge/commands/evangelosmeklis/thufir/analyze-prometheus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,552 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.01552
Opus 5 $0.00008 $0.00776
Sonnet 5 $0.00003 $0.00310
Haiku 4.5 $0.00002 $0.00155

Measured 8d ago against content hash 5e506e4d12ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

analyze-prometheus 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 8d 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.

commands/analyze-prometheus.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Prometheus Alert Command

Purpose

Investigate a Prometheus alert by fetching alert details, querying related metrics, searching the codebase for relevant code, analyzing git history, and generating a root cause analysis report.

Instructions for Claude

When this command is invoked, perform comprehensive root cause analysis for a Prometheus alert:

Step 1: Gather Alert Information

If user provided alert name:

  1. Use prometheus MCP tool to fetch alert details
  2. Extract alert expression, labels, severity, and active time

If user provided alert JSON:

  1. Parse the alert JSON
  2. Extract key fields: alertname, expr, labels, annotations, activeAt

If no argument provided:

  1. Use AskUserQuestion to ask:
    • "What is the alert name?"
    • Or "Please paste the alert JSON"
  2. Fetch or parse accordingly

Extract from alert:

  • Alert name
  • PromQL expression that triggered
  • Threshold value
  • Time alert started firing
  • Affected labels (service, instance, job, etc.)
  • Alert severity
  • Alert annotations (description, summary)

Step 2: Query Prometheus Metrics

Use prometheus MCP tools to query related metrics:

  1. Execute alert expression to see current value:

    • Query the alert's PromQL expression
    • Check how far above threshold the metric is
  2. Query metric over time to see pattern:

    • Use query_range for last 2-6 hours
    • Identify: sudden spike, gradual increase, or other pattern
  3. Query breakdown metrics:

    • Break down by labels (endpoint, instance, status code)
    • Identify which specific component is affected
  4. Query correlated metrics:

    • Error rate metrics
    • Latency metrics (p95, p99)
    • Resource usage (CPU, memory)
    • Request rate metrics
    • Dependency health metrics
  5. Analyze metric patterns:

    • When did anomaly start?
    • Sudden or gradual?
    • Correlated with other metric changes?

Step 3: Search Codebase

Based on alert and metrics, search code for relevant files:

  1. From alert labels, identify:
    • Service name
    • Endpoint or feature affected
    • Component mentioned in annotations

Read the full file on GitHub · 228 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. 8d ago First seen · 228 lines · 15 tokens per session scan A 5e506e4d12ad

Subscribe to this mod's changes

analyze-prometheus is a command published in the GitHub repository evangelosmeklis/thufir (7 stars, last pushed 8mo ago), licensed MIT. It adds 15 tokens to every session and 1,552 once invoked, about $0.0001 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.