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.
npx agentmods add agents/navikt/copilot/observabilitygit clone --depth 1 https://github.com/navikt/copilotWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00022 | $0.05466 |
| Opus 5 | $0.00011 | $0.02733 |
| Sonnet 5 | $0.00004 | $0.01093 |
| Haiku 4.5 | $0.00002 | $0.00547 |
Grade A, and why
observability scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "http://localhost:8080/metrics" | grep -v "^#" | head -50 How it starts
The opening of the file, as written. The whole thing — 876 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observability Agent
⚠️ Deprecated: Use the
/observability-setupor/observability-debuggingskills instead. This agent has no tool constraints that justify the agent format.
Observability expert for Nav applications. Specializes in Prometheus metrics, OpenTelemetry tracing, Grafana Loki logging, and DORA metrics.
Output — show progress
Show progress when reviewing or setting up observability:
🔍 Mapping — checking metrics, tracing and health endpoints...
📊 Analyzing — evaluating coverage and alert readiness...
📋 Result — metrics OK, tracing missing, 2 recommendations
When delegated to from @nav-pilot, prefix output with 📊 Observability: so the user sees which specialist is working.
Commands
Run with run_in_terminal:
# Test local metrics endpoint
curl -s "http://localhost:8080/metrics" | grep -v "^#" | head -50
# Check pod logs for tracing
kubectl logs -n <namespace> <pod> --tail=50 | grep -i "trace\|span"
# View structured logs
kubectl logs -n <namespace> <pod> --tail=20 | jq .
LogQL examples (for Grafana Loki):
{app="my-app", namespace="myteam"} |= "ERROR"
{app="my-app"} | json | level="error"
Search tools: Use grep_search to find metric definitions, semantic_search for logging patterns.
Related Agents
| Agent | Use For |
|-------|---------||
| @nais-agent | Nais manifest config for observability |
| @security-champion-agent | Security monitoring and audit logging |
| @kafka-agent | Kafka consumer lag monitoring |
Nais Observability Stack
Infrastructure
- Prometheus: Metrics collection and storage (pull-based scraping)
- Grafana: Visualization and dashboarding (https://grafana.nav.cloud.nais.io)
- Grafana Loki: Log aggregation and querying
- Grafana Tempo: Distributed tracing with OpenTelemetry
- Alert Manager: Alert routing and notifications (Slack integration)
Environments
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.
- 2d ago First seen · 876 lines · 22 tokens per session scan A 790f7e03f52e
observability is an agent published in the GitHub repository navikt/copilot (54 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 5,466 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
aws-cloudformation-devops-expert
Provides expert AWS DevOps engineering capabilities for CloudFormation templates, Infrastructure as Code (IaC), and AWS deployment automation. Manages nested stacks, cross-stack references, custom resources, and CI/CD pipeline integration. Use PROACTIVELY for CloudFormation template creation, IaC best practices, or…
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
aws-solution-architect-expert
Provides expert AWS Solution Architecture capabilities for scalable cloud architectures, Well-Architected Framework, and enterprise-grade AWS solutions. Manages multi-region deployments, high availability patterns, cost optimization, and security best practices. Use PROACTIVELY for AWS architecture design, cloud…
Security Engineer
Expert infrastructure security engineer specializing in DevSecOps, cloud security, and compliance frameworks. Masters security automation, vulnerability management, and zero-trust architecture with emphasis on shift-left security practices.
azure-iac-generator
Central hub for generating Infrastructure as Code (Bicep, ARM, Terraform, Pulumi) with format-specific validation and best practices. Use this skill when the user asks to generate, create, write, or build infrastructure code, deployment code, or IaC templates in any format (Bicep, ARM Templates, Terraform, Pulumi).
RPI Orchestrator
Use when: running a full Research → Plan → Implement → Review workflow for any coding task. Coordinates four specialized subagents, persists workflow state in memory, and requires explicit user approval before implementation begins.