obs-guardian

obs-guardian is a skill for Claude Code from mturac/hermes-supercode-skills. It costs 165 tokens per session (1,781 once invoked), scanned A, original, MIT.

An observability guide for making production software easier to monitor and diagnose. Observability means collecting traces, metrics, and logs that show what a system is doing and where failures occur.

In plain words
What is it for?
Use it to add OpenTelemetry instrumentation, structured logs, correlation IDs, Prometheus and Grafana monitoring, distributed tracing, alerts, and incident runbooks.
Why use it?
It connects technical signals and alerts to user impact, helping teams investigate incidents without relying on noisy or incomplete information.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the api-sculptor plugin — 13 skills shipped together , and of auth-architect, db-whisperer, deploy-ninja, ghost-scraper, infra-automation, mcp-conductor, obs-guardian, pipeline-architect, prediction-alpha, prompt-forge, quantum-debugger, security-sentinel

Good fit Use it to add OpenTelemetry instrumentation, structured logs, correlation IDs, Prometheus and Grafana monitoring, distributed tracing, alerts, and incident runbooks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mturac/hermes-supercode-skills/obs-guardian
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 mturac/hermes-supercode-skills --skill obs-guardian
Clone the repo
git clone --depth 1 https://github.com/mturac/hermes-supercode-skills

Made for: Claude Code.

Or install api-sculptor, the plugin that ships this one along with the rest of its 13 skills.

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 obs-guardian

README.md
[![agentmods](https://agentmods.dev/badge/skills/mturac/hermes-supercode-skills/obs-guardian.svg)](https://agentmods.dev/skills/mturac/hermes-supercode-skills/obs-guardian)
Your own site
<a href="https://agentmods.dev/skills/mturac/hermes-supercode-skills/obs-guardian"><img src="https://agentmods.dev/badge/skills/mturac/hermes-supercode-skills/obs-guardian.svg" alt="Measured on agentmods" height="20"></a>
Per session 165 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,781 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 $0.00165 $0.01781
Opus 5 $0.00082 $0.00890
Sonnet 5 $0.00033 $0.00356
Haiku 4.5 $0.00016 $0.00178

Measured 8d ago against content hash 675f2eeab000, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

obs-guardian 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.

skills/obs-guardian/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Obs Guardian

You are an observability and incident visibility specialist. You make systems explain themselves through useful telemetry, actionable alerts, and runbooks that reduce time to diagnosis. You prefer signals tied to user impact over noisy dashboards, and you avoid changes that hide production failures.

Core Concepts

Telemetry Signals

  • Traces: request flow across services, queues, and databases
  • Metrics: numeric time series for health, saturation, latency, errors, throughput, and business-critical behavior
  • Logs: structured event records with context, correlation IDs, and stable field names
  • Profiles: CPU, memory, and lock contention for deeper performance work

OpenTelemetry

  • Instrument at service entry, outbound calls, database queries, queues, and background jobs
  • Propagate trace context across HTTP, messaging, and worker boundaries
  • Use the Collector to receive, process, sample, and export telemetry
  • Keep resource attributes consistent: service name, version, environment, region, and instance

Alerting

  • Page on user-impacting symptoms, not every internal cause
  • Use SLO burn-rate alerts for availability and latency objectives
  • Route warnings to tickets or chat; route urgent symptoms to on-call
  • Every page needs a runbook, owner, severity, and clear mitigation path

Workflow

1. Recon

Map the system and current visibility:

Services:
  - api
  - worker
  - billing
Telemetry:
  metrics: prometheus
  dashboards: grafana
  traces: tempo
  logs: json to loki
Incident Gaps:
  - no trace propagation between api and worker
  - no burn-rate alert for checkout errors
  - logs missing request_id

Collect service language/framework, deployment platform, current agents, existing alerts, dashboard links, incident examples, and on-call routing.

2. Plan

Choose the smallest visibility improvement that answers the user's problem:

If no visibility:
  - add request metrics
  - add structured logs with request_id and trace_id
  - add traces around inbound and outbound calls

If incidents are missed:
  - define SLO
  - add burn-rate alerts
  - route alerts to on-call

If logs exist but cannot be joined:
  - standardize fields
  - propagate correlation IDs
  - add trace_id and span_id to logs

Read the full file on GitHub · 253 lines

Files

What ships with it

1 file 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. 8d ago First seen · 253 lines · 165 tokens per session scan A 675f2eeab000

Subscribe to this mod's changes

obs-guardian is a skill published in the GitHub repository mturac/hermes-supercode-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 165 tokens to every session and 1,781 once invoked, about $0.0008 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

csharp-coding-standards

Defines the C# coding standards, patterns, and conventions to be applied consistently across all C# projects. Rules cover naming, structure, async patterns, null handling, dependency injection, logging, result patterns, and formatting. Apply these rules uniformly in all production code.

linuxchata/ai-playbook · 61 tokens

csharp-api-controller-standards

Defines the coding standards, patterns, and conventions for ASP.NET Core REST API controllers. Rules cover routing, HTTP verbs, response types, XML documentation, dependency injection, and asynchronous execution. Apply these rules uniformly to ensure a consistent, predictable, and well-documented API surface.

linuxchata/ai-playbook · 63 tokens

csharp-testing-standards

Defines the testing standards, patterns, and conventions for all C# unit and integration test projects. Rules cover test framework usage, naming, structure, mocking, assertions, and parameterization. Apply these rules uniformly across all test projects.

linuxchata/ai-playbook · 53 tokens

swift-networking

Builds a protocol-based async/await networking layer with URLSession, testable abstractions, error handling, and mock support for Swift projects. Use when user says "add networking", "create an API layer", "fetch data from API", "build a network service", "add URLSession", "implement HTTP requests", "create a REST…

jeremieb/swift-unit-test-instructions · 82 tokens

[object Object]

Rules, skills, and guidelines for AI coding assistants – Claude, Cursor, and beyond.

linuxchata/ai-playbook · 8 tokens

swift-architecture-audit

Audits an existing Swift/SwiftUI/UIKit codebase for MVVM compliance, testability issues, architectural violations, concurrency problems, and anti-patterns. Use when user says "audit the codebase", "review the architecture", "why is this hard to test", "onboard to this project", "analyze the code structure", "find…

jeremieb/swift-unit-test-instructions · 88 tokens