Agent skill

Prometheus Monitoring

by automateyournetwork in automateyournetwork/netclaw

Prometheus monitoring — PromQL instant/range queries, metric discovery, metadata, scrape target health, system health checks (6 tools).

Apache-2.0Auto-check: notesDevOps & Cloud

Install Prometheus Monitoring

skills CLI
$ npx skills add automateyournetwork/netclaw --skill prometheus-monitoring -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install automateyournetwork/netclaw prometheus-monitoring --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/automateyournetwork/netclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/workspace/skills/prometheus-monitoring .claude/skills/prometheus-monitoring && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
prometheus-monitoring
GitHub stars
676
Token cost
~2k tokens
SKILL.md length
658 words
Files
1
Skills in repo
120
Repo updated
First seen
Licence
Apache-2.0

At a glance

Prometheus monitoring — PromQL instant/range queries, metric discovery, metadata, scrape target health, system health checks (6 tools).

  • Works in 7 steps: Health check: health_check — verify… → Discover metrics: list_metrics — find… → Metric metadata:… → …
  • Lightweight Prometheus query with no Grafana dashboard involved: querying Prometheus metrics
  • SKILL.md covers MCP Server, How to Run, Environment Variables and Tools, plus 6 more sections
  • Calls pip3; needs PROMETHEUS_PASSWORD and PROMETHEUS_TOKEN

What it does

Prometheus Monitoring is an agent skill from automateyournetwork/netclaw. Prometheus monitoring — PromQL instant/range queries, metric discovery, metadata, scrape target health, system health checks (6 tools). Use for a direct, lightweight Prometheus query with no Grafana dashboard involved: querying Prometheus metrics, checking scrape targets, investigating alert thresholds, or analyzing network device utilization trends. If the task also needs Grafana dashboards, Loki logs, alerting/OnCall, or panel rendering, use grafana-observability instead.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Monitoring and alerting. It works with Prometheus, Grafana and Model Context Protocol. The repository describes itself as: An AI agent that claws through your network. The licence is Apache-2.0.

When your agent uses it

  • Lightweight Prometheus query with no Grafana dashboard involved: querying Prometheus metrics
  • Checking scrape targets
  • Investigating alert thresholds
  • Analyzing network device utilization trends

Example prompts

  • “/prometheus-monitoring”

Requirements

  • Python 3
  • A credential in PROMETHEUS_TOKEN

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Health check: health_check — verify Prometheus is reachable
  2. Discover metrics: list_metrics — find available SNMP/device metrics
  3. Metric metadata: get_metric_metadata(metric="ifHCInOctets") — check type and description
  4. Instant query: execute_query(query="up{job='snmp'}") — check which targets are up
  5. Range query: execute_range_query — trend analysis over time
  6. Scrape targets: get_targets — verify SNMP exporters and device scrape health
  7. GAIT: Record all queries in audit trail

What it can do on your machine

Read from SKILL.md and the folder at commit aa90e7d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • PROMETHEUS_PASSWORD
    • PROMETHEUS_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prometheus Monitoring loads about 2k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 658 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:145
    `, or `PROMETHEUS_TOKEN` in `~/.openclaw/.env`. Verify Prometheus allows the configured auth method.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from automateyournetwork/netclaw at commit aa90e7d, republished under its Apache-2.0 licence (© automateyournetwork). 658 words, ~2,029 tokens.

Download SKILL.mdSave it as .claude/skills/prometheus-monitoring/SKILL.md (or your agent's skills folder).
name
prometheus-monitoring
description
Prometheus monitoring — PromQL instant/range queries, metric discovery, metadata, scrape target health, system health checks (6 tools). Use for a direct, lightweight Prometheus query with no Grafana dashboard involved: querying Prometheus metrics, checking scrape targets, investigating alert thresholds, or analyzing network device utilization trends. If the task also needs Grafana dashboards, Loki logs, alerting/OnCall, or panel rendering, use `grafana-observability` instead.
license
Apache-2.0
user-invocable
true

Prometheus Monitoring

MCP Server

PropertyValue
Sourcepab1it0/prometheus-mcp-server
Transportstdio (default), SSE, or HTTP
LanguagePython 3.10+
Tools6 (query, range query, list metrics, metadata, targets, health check)
AuthBasic auth (username/password), bearer token, or unauthenticated
Installpip3 install prometheus-mcp-server (PyPI)
Runprometheus-mcp-server (stdio)

How to Run

bash
# stdio mode (default — used by NetClaw)
PROMETHEUS_URL=http://prometheus:9090 prometheus-mcp-server

# HTTP transport mode
PROMETHEUS_MCP_SERVER_TRANSPORT=http PROMETHEUS_URL=http://prometheus:9090 prometheus-mcp-server

# With basic auth
PROMETHEUS_URL=http://prometheus:9090 PROMETHEUS_USERNAME=admin PROMETHEUS_PASSWORD=secret prometheus-mcp-server

# With bearer token (Grafana Cloud, Thanos, etc.)
PROMETHEUS_URL=https://prom.example.com PROMETHEUS_TOKEN=your_bearer_token prometheus-mcp-server

Environment Variables

VariableRequiredExampleDescription
PROMETHEUS_URLYeshttp://prometheus:9090Prometheus server endpoint
PROMETHEUS_USERNAMENoadminBasic auth username
PROMETHEUS_PASSWORDNochangemeBasic auth password
PROMETHEUS_TOKENNoeyJhbG...Bearer token (Grafana Cloud, Thanos, Cortex)
PROMETHEUS_URL_SSL_VERIFYNofalseDisable SSL certificate verification
PROMETHEUS_REQUEST_TIMEOUTNo30Request timeout in seconds (default: 30)
PROMETHEUS_DISABLE_LINKSNotrueDisable Prometheus UI links in responses (saves context)
ORG_IDNo1Multi-tenant organization ID (Cortex/Mimir)
PROMETHEUS_CUSTOM_HEADERSNo{"X-Custom":"val"}Additional HTTP headers as JSON
PROMETHEUS_MCP_SERVER_TRANSPORTNostdioTransport: stdio (default), http, or sse

Tools

ToolParametersWhat It Does
execute_queryquery, timeout?Execute instant PromQL query at current time
execute_range_queryquery, start, end, step, timeout?Execute PromQL range query over time interval
list_metricspage?, page_size?Browse available metric names with pagination
get_metric_metadatametric?, limit?Retrieve metric type, help text, and unit info
get_targetsnoneView scrape target details (up/down, labels, last scrape)
health_checknoneCheck Prometheus server availability and readiness

Workflow: Network Device Metric Monitoring

When checking Prometheus for network device metrics:

  1. Health check: health_check — verify Prometheus is reachable
  2. Discover metrics: list_metrics — find available SNMP/device metrics
  3. Metric metadata: get_metric_metadata(metric="ifHCInOctets") — check type and description
  4. Instant query: execute_query(query="up{job='snmp'}") — check which targets are up
  5. Range query: execute_range_query — trend analysis over time:
    • Interface traffic: rate(ifHCInOctets{instance="router1"}[5m]) * 8
    • CPU utilization: device_cpu_utilization{device="core-rtr-01"}
    • Interface errors: increase(ifInErrors{device=~".*"}[1h])
    • BGP peer state: bgp_peer_state{peer="10.1.1.2"}
  6. Scrape targets: get_targets — verify SNMP exporters and device scrape health
  7. GAIT: Record all queries in audit trail
Example: Interface Utilization Check
health_check()
list_metrics(page=1, page_size=50)
execute_query(query="rate(ifHCInOctets{device='core-rtr-01'}[5m]) * 8")
execute_range_query(query="rate(ifHCOutOctets{device='core-rtr-01'}[5m]) * 8", start="2024-01-01T00:00:00Z", end="2024-01-01T01:00:00Z", step="60s")
get_targets()

Workflow: Alert Threshold Investigation

When investigating whether metrics are crossing alert thresholds:

  1. Discover metrics: list_metrics — find the metric name
  2. Check metadata: get_metric_metadata — understand metric type (counter, gauge, histogram)
  3. Current value: execute_query — get current metric value
  4. Historical trend: execute_range_query — check trend over past 1h/6h/24h
  5. Compare targets: get_targets — check if specific exporters are down
  6. Report: Metric analysis with current value, trend direction, and recommendation

Workflow: Capacity Planning

When analyzing capacity trends for network infrastructure:

  1. Discover metrics: list_metrics — find bandwidth/utilization metrics
  2. Peak analysis: execute_range_query with max_over_time():
    • max_over_time(rate(ifHCInOctets{device="core-rtr-01",ifName="Gi0/0"}[5m])[7d:1h]) * 8
  3. 95th percentile: execute_range_query with quantile_over_time():
    • quantile_over_time(0.95, rate(ifHCInOctets{device="core-rtr-01"}[5m])[30d:1h]) * 8
  4. Growth rate: Compare weekly/monthly averages
  5. Report: Utilization summary with capacity headroom and growth projection

Show full SKILL.md (252 more words)Show less

Integration with Other Skills

SkillIntegration
grafana-observabilityGrafana dashboards visualize Prometheus data; use Prometheus skill for direct PromQL when Grafana isn't available or for ad-hoc queries
pyats-health-checkCross-reference pyATS device health with Prometheus time-series metrics
pyats-routingCorrelate OSPF/BGP state changes with Prometheus metric timelines
gait-session-trackingRecord all Prometheus queries and findings in GAIT audit trail
te-network-monitoringPair ThousandEyes path data with Prometheus infrastructure metrics
sdwan-opsCorrelate SD-WAN vManage alarms with Prometheus device metrics
servicenow-change-workflowReference Prometheus metrics as evidence in change requests

Important Rules

  • Prefer read-only operations — all 6 tools are read-only; no Prometheus configuration changes
  • Use pagination for metric lists — list_metrics supports page and page_size to avoid large responses
  • Specify time ranges carefully — overly broad execute_range_query time ranges return large result sets
  • Disable links for context efficiency — set PROMETHEUS_DISABLE_LINKS=true to reduce response size
  • GAIT audit mandatory — record all Prometheus queries and metric analysis in audit trail
  • No secrets in queries — never embed credentials or sensitive data in PromQL expressions
  • Verify connectivity first — use health_check before running queries to confirm Prometheus is reachable

Error Handling

  • Auth fails (401/403): Check PROMETHEUS_URL, PROMETHEUS_USERNAME/PROMETHEUS_PASSWORD, or PROMETHEUS_TOKEN in ~/.openclaw/.env. Verify Prometheus allows the configured auth method.
  • Connection refused: Verify PROMETHEUS_URL is reachable. Use health_check to diagnose connectivity.
  • PromQL syntax errors: Use list_metrics and get_metric_metadata to discover valid metric names before querying.
  • Empty results: Check get_targets to verify scrape targets are up and the expected labels exist.
  • Timeout errors: Increase PROMETHEUS_REQUEST_TIMEOUT for slow queries or large result sets.
  • SSL errors: Set PROMETHEUS_URL_SSL_VERIFY=false for self-signed certificates (development only).

© automateyournetwork, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in workspace/skills/prometheus-monitoring of automateyournetwork/netclaw.

Open the folder on GitHubat commit aa90e7d

Compare with similar skills

Prometheus Monitoring next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prometheus Monitoring compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prometheus Monitoring this skillautomateyournetwork/netclaw676—~2kAutomated safety check: NotesApache-2.0
Syncmetapawurb/hotpath-rs1.9k—~1.2kAutomated safety check: NotesMIT
Archestra Dev Observabilityarchestra-ai/archestra4.4k—~1.2kAutomated safety check: PassCustom licence
Frontmcp Observabilityagentfront/frontmcp146—~4.6kAutomated safety check: PassApache-2.0
Live Debugmacro-inc/macro4.6k—~2.4kAutomated safety check: NotesAGPL-3.0
Analyzing Experiment Precompute CanaryPostHog/posthog40k—~3.5kAutomated safety check: PassCustom licence

Similar skills

  • Syncmeta

    pawurb/hotpath-rs

    Sync changes from the hotpath, hotpath-macros and hotpath-drain crates to their meta counterparts (hotpath-meta, hotpath-macros-meta and hotpath-drain-meta).

    1.9k GitHub stars~1.2k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Archestra Dev Observability

    archestra-ai/archestra

    A skill your agent uses when changing Archestra tracing, metrics, OpenTelemetry, Tempo, Grafana, Prometheus, LLM/MCP spans, observability labels, or local observability setup.

    4.4k GitHub stars~1.2k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Frontmcp Observability

    agentfront/frontmcp

    A skill your agent uses when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server.

    146 GitHub stars~4.6k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Live Debug

    macro-inc/macro

    Debug the running local stack with traces, logs, and a shared headless browser.

    4.6k GitHub stars~2.4k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Analyze the experiment precompute result-consistency canary across prod-US and prod-EU, deep-dive any issues, and produce an actionable report.

    40k GitHub stars~3.5k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Ops Report

    haacked/dotfiles

    Generate a 24-hour operational health report for a PostHog service by querying Grafana dashboards and Prometheus metrics.

    134 GitHub stars~8k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes

More from automateyournetwork/netclaw

All 120 skills in this repo
  • EVE-NG Lab Topology Design

    automateyournetwork/netclaw

    Entry point for designing EVE-NG network labs: classifies the request, gathers missing requirements, proposes options and validates the resulting topology.

    677 GitHub stars~612 tokensUpdated today
    Auto-check passed
  • ACI Policy Change Deployment

    automateyournetwork/netclaw

    Deploys Cisco ACI policy changes only behind an approved ServiceNow Change Request, capturing pre and post-change fault baselines and rolling back automatically on a fault delta.

    677 GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Cisco ACI Fabric Health Audit

    automateyournetwork/netclaw

    Runs a phased health audit of a Cisco ACI fabric through MCP tools: node status, links, tenant and policy review, faults and endpoint learning.

    677 GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Anta Validation

    automateyournetwork/netclaw

    Validate Arista EOS network state against ANTA's pre-built 208-test catalogue, with structured pass/fail verdicts.

    677 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Arista Cvp

    automateyournetwork/netclaw

    Arista CloudVision Portal (CVP) automation via REST API — device inventory, events, connectivity monitoring, tag management (4 tools).

    677 GitHub stars~2.2k tokensUpdated today
    Auto-check: notes
  • AWS Cloud Monitoring

    automateyournetwork/netclaw

    AWS CloudWatch monitoring — metrics, alarms, log queries, VPC flow log analysis, network performance.

    677 GitHub stars~1k tokensUpdated today
    Auto-check passed

Categories

Questions about Prometheus Monitoring

What does Prometheus Monitoring do?

Prometheus monitoring — PromQL instant/range queries, metric discovery, metadata, scrape target health, system health checks (6 tools). Prometheus Monitoring is an agent skill from automateyournetwork/netclaw. Prometheus monitoring — PromQL instant/range queries, metric discovery, metadata, scrape target health, system health checks (6 tools).

When should I use Prometheus Monitoring?

Prometheus Monitoring fits situations like: lightweight Prometheus query with no Grafana dashboard involved: querying Prometheus metrics; checking scrape targets; investigating alert thresholds; analyzing network device utilization trends.

How do I install Prometheus Monitoring in Claude Code?

Run `npx skills add automateyournetwork/netclaw --skill prometheus-monitoring -a claude-code`. Or copy the skill folder (workspace/skills/prometheus-monitoring in automateyournetwork/netclaw) into .claude/skills/prometheus-monitoring in your project. Claude Code loads it when a task matches its description.

How do I install Prometheus Monitoring in Codex?

Run `npx skills add automateyournetwork/netclaw --skill prometheus-monitoring -a codex`. Or copy the skill folder (workspace/skills/prometheus-monitoring in automateyournetwork/netclaw) into .agents/skills/prometheus-monitoring in your project. Codex loads it when a task matches its description.

Can I use Prometheus Monitoring in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add automateyournetwork/netclaw --skill prometheus-monitoring -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prometheus-monitoring, .gemini/skills/prometheus-monitoring, .github/skills/prometheus-monitoring and .opencode/skills/prometheus-monitoring in your project.

What does Prometheus Monitoring need to run?

Going by SKILL.md and its folder, Prometheus Monitoring needs the command-line tools its instructions call (pip3) and credentials named PROMETHEUS_PASSWORD and PROMETHEUS_TOKEN. Our summary lists: Python 3; A credential in PROMETHEUS_TOKEN.

Does Prometheus Monitoring access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Prometheus Monitoring safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Prometheus Monitoring use?

Prometheus Monitoring is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prometheus Monitoring use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prometheus Monitoring?

Skills that share tags, products or a category with Prometheus Monitoring: Syncmeta (pawurb/hotpath-rs, 1.9k stars), Archestra Dev Observability (archestra-ai/archestra, 4.4k stars), Frontmcp Observability (agentfront/frontmcp, 146 stars) and Live Debug (macro-inc/macro, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prometheus Monitoring?

automateyournetwork (a GitHub user) maintains it in automateyournetwork/netclaw, which has 676 GitHub stars. The repository holds 120 skills in this directory. The repository was last updated on October 9, 2026.

Source: automateyournetwork/netclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.