anomalies

anomalies is a command for coding agents from danielbodnar/skills. It costs 0 tokens per session (264 once invoked), scanned A, original, MIT.

A command that uses Netdata, a system-monitoring tool, to find metrics behaving unusually. It reports anomaly rates, context, severity, and related unusual metrics.

In plain words
What is it for?
Use it to review the last hour of system metrics, group findings by severity, compare them with known baselines, check for correlations, and get recommendations for significant anomalies.
Why use it?
It helps separate expected variation from behavior that may signal a fault or incident. It also puts findings in one report instead of requiring manual metric checking.

Command

Part of the infra-ops plugin — 3 skills, 12 commands, 1 agent shipped together

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/danielbodnar/skills/anomalies
Clone the repo
git clone --depth 1 https://github.com/danielbodnar/skills

Or install infra-ops, the plugin that ships this one along with the rest of its 3 skills, 12 commands, 1 agent.

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 anomalies

README.md
[![agentmods](https://agentmods.dev/badge/commands/danielbodnar/skills/anomalies.svg)](https://agentmods.dev/commands/danielbodnar/skills/anomalies)
Your own site
<a href="https://agentmods.dev/commands/danielbodnar/skills/anomalies"><img src="https://agentmods.dev/badge/commands/danielbodnar/skills/anomalies.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 264 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 $0.00000 $0.00264
Opus 5 $0.00000 $0.00132
Sonnet 5 $0.00000 $0.00053
Haiku 4.5 $0.00000 $0.00026

Measured 4d ago against content hash 4dde795f7c7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

anomalies 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.

plugins/infra-ops/commands/anomalies.md · 32 lines

What it actually says

Anomaly Detection Report

Use Netdata's ML-powered anomaly detection to identify unusual system behavior:

  1. Find anomalous metrics in the last 1 hour:

    • Set cardinality_limit to 30 for top anomalies
    • Include anomaly rate percentages
    • Show min/max/avg values for context
  2. For each anomaly found:

    • Explain what the metric represents
    • Show the anomaly rate (% of samples that were anomalous)
    • Identify if this is concerning or expected behavior
    • Provide context from system knowledge (CLAUDE.md)
  3. Categorize anomalies by severity:

    • 🔴 Critical (>10% anomaly rate or system-critical metrics)
    • 🟡 Warning (5-10% anomaly rate)
    • 🔵 Info (1-5% anomaly rate or expected variations)
  4. Check for correlated anomalies:

    • Do multiple related metrics show anomalies?
    • Are anomalies concentrated in specific time windows?
    • Are they related to known incidents?
  5. Compare to baseline from CLAUDE.md:

    • SSH threads (12.5% anomaly rate - known)
    • WireGuard drops (4.1% - investigate)
    • Container CPU spikes (3.3% - monitor)

Provide actionable recommendations for each significant anomaly.

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. 4d ago First seen · 32 lines · 0 tokens per session scan A 4dde795f7c7f

Subscribe to this mod's changes

anomalies is a command published in the GitHub repository danielbodnar/skills (2 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 264 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 2026-08-31.