observability-audit

observability-audit is a skill for Claude Code from karsten-s-nielsen/mad-scientist-skills. It costs 123 tokens per session (9,723 once invoked), scanned A, original, MIT.

A review of whether a system produces enough useful information about its own operation. It covers planning monitoring for a new system or checking existing logs, measurements, traces, alerts, data pipelines, and machine-learning models.

In plain words
What is it for?
Use it to design monitoring, define service targets, review instrumentation, check alerts and pipelines, and assess monitoring before production release.
Why use it?
It reveals blind spots that can make failures, slowdowns, broken data flows, or model changes difficult to detect and diagnose.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the mad-scientist-skills plugin — 10 skills, 4 commands shipped together

Good fit Use it to design monitoring, define service targets, review instrumentation, check alerts and pipelines, and assess monitoring before production release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/karsten-s-nielsen/mad-scientist-skills/observability-audit
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.

Any agent
npx skills add karsten-s-nielsen/mad-scientist-skills --skill observability-audit
Clone the repo
git clone --depth 1 https://github.com/karsten-s-nielsen/mad-scientist-skills

Made for: Claude Code.

Or install mad-scientist-skills, the plugin that ships this one along with the rest of its 10 skills, 4 commands.

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 observability-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/observability-audit/github.svg)](https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/observability-audit)
Your own site
<a href="https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/observability-audit"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/observability-audit/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 observability-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/observability-audit"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/observability-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,723 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 $0.00123 $0.09723
Opus 5 $0.00062 $0.04862
Sonnet 5 $0.00025 $0.01945
Haiku 4.5 $0.00012 $0.00972

Measured 12d ago against content hash 83c320a5b5c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

observability-audit 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 12d 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/mad-scientist-skills/skills/observability-audit/SKILL.md · 727 lines

How it starts

The opening of the file, as written. The whole thing — 727 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Observability Audit

A comprehensive observability skill with two modes and two tiers:

Modes:

  • Planning (before code exists) — telemetry strategy, SLI/SLO design, instrumentation architecture
  • Audit (on existing code) — scanning for observability gaps in logging, metrics, tracing, alerting, pipelines, and ML models

Tiers (applied within each phase):

  • Standard — free/open-source tools, code-level patterns, OpenTelemetry-native. Always actionable for any developer.
  • Enterprise — paid observability platforms (Datadog, New Relic, Splunk, etc.). Serves as a professional checklist documenting what enterprise teams should implement.

Core question: "Can you see what your system is doing?"

When to use this skill

  • When the user says "observability audit", "check monitoring", "find blind spots", "audit telemetry", "design observability", or "review instrumentation"
  • Before designing a new system (planning mode) — to define telemetry strategy and SLIs/SLOs early
  • On an existing codebase (audit mode) — to find and fix observability gaps
  • Before a production deployment — to validate monitoring and alerting posture
  • After adding new services, data pipelines, or ML models
  • When investigating production incidents caused by insufficient observability

Mode detection

Determine which mode to operate in based on the project state:

Signal Mode Rationale
User says "design observability", "telemetry strategy", "define SLOs" Planning Architecture-level analysis before code
User says "audit", "check monitoring", "find blind spots" Audit Code and infrastructure scanning
No source code exists yet (only docs, diagrams, RFCs) Planning Nothing to scan — design telemetry instead
Source code and/or infrastructure files exist Audit Concrete artifacts to analyze
Both code and a request to "design observability" Both Run planning phases on architecture, audit phases on code

Read the full file on GitHub · 727 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 727 lines · 123 tokens per session scan A 83c320a5b5c0

Subscribe to this mod's changes

observability-audit is a skill published in the GitHub repository karsten-s-nielsen/mad-scientist-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 123 tokens to every session and 9,723 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

concept

This skill should be used when the user asks to "create a concept spec", "retrofit a module", "check spec drift", "run drift detection", "design a new module", "wyx concept", or wants to generate, update, or drift-check CONCEPT.md files. Supports retrofit, greenfield, drift detection, and discovery modes.

jlifyio/wyx · 73 tokens

map

This skill should be used when the user asks to "generate architecture map", "visualize spec relationships", "create ARCHITECTURE.md", "show concept dependencies", "wyx map", or wants a Mermaid graph with dependency matrix and data flow paths derived from all wyx specs.

jlifyio/wyx · 60 tokens

audit

This skill should be used when the user asks to "audit spec coverage", "find uncovered modules", "scan for missing specs", "check wyx coverage", "get spec TODO list", "wyx audit", "wyx", or wants a prioritized list of wyx skill commands for uncovered modules. Scans for coverage gaps, pipeline/sync candidates, and…

jlifyio/wyx · 81 tokens

sync

This skill should be used when the user asks to "document sync patterns", "map sync handlers", "create SYNCS.md", "review sync coordination", "wyx sync", or wants to understand how concepts communicate through orchestrated workflows. Produces SYNCS.md coordination maps.

jlifyio/wyx · 58 tokens

pipeline

This skill should be used when the user asks to "create a pipeline spec", "document data transformations", "document data flow", "specify pipeline invariants", "wyx pipeline", or wants to design, retrofit, or discover data pipelines with quality invariants and boundary ownership. Produces PIPELINE.md specs.

jlifyio/wyx · 66 tokens

refactor

Automated iterative code refactoring with swarm-orchestrated specialist agents including deep codebase discovery, confidence-scored code review, and security analysis. Use this skill when the user wants to improve existing code quality, clean up messy code, restructure, simplify, reduce tech debt, or perform…

zircote-plugins/refactor · 112 tokens