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 skills add navikt/copilot --skill observability-debugginggit clone --depth 1 https://github.com/navikt/copilotWrote 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.
[](https://agentmods.dev/skills/navikt/copilot/observability-debugging)<a href="https://agentmods.dev/skills/navikt/copilot/observability-debugging"><img src="https://agentmods.dev/badge/skills/navikt/copilot/observability-debugging/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.
<a href="https://agentmods.dev/skills/navikt/copilot/observability-debugging"><img src="https://agentmods.dev/badge/skills/navikt/copilot/observability-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 53 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 306 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.04700 |
| Opus 5.5 | $0.00015 | $0.01880 |
| Sonnet 5.5 | $0.00008 | $0.00940 |
| Haiku 4.5 | $0.00004 | $0.00470 |
Grade A, and why
observability-debugging scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Why a wrapper rather than a hand-written `curl`: these four hosts sit behind two cplt gates and a Mimir tenant header, and each refuses a request differently. Piped into `jq`, every one of them arrives as `parse error: I How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observability debugging with three-pillar diagnostics
Structured debugging workflows using Nav's observability stack. Replaces guesswork with systematic investigation across metrics, logs, and traces.
Mental Model
| Pillar | Tool | Answers | Endpoint |
|---|---|---|---|
| Metrics | Mimir (Prometheus) | What is happening? (rates, quantiles, saturation) | mimir.nav.cloud.nais.io |
| Logs | Loki | Why is it happening? (errors, context, messages) | loki.nav.cloud.nais.io |
| Traces | Tempo | Where in the call chain? (latency, dependencies) | tempo.$env.nav.cloud.nais.io |
Debugging Workflow
Symptom
├── High error rate → Start with Metrics (Mimir)
│ └── Find failing endpoint → Logs → Traces
├── Slow responses → Start with Metrics (latency quantiles)
│ └── Find slow endpoint → Traces → Identify bottleneck
├── Specific user error → Start with Logs (Loki)
│ └── Find trace_id → Tempo → See full call chain
├── Intermittent failures → Start with Traces (Tempo)
│ └── Filter by error status → Correlate with Metrics/Logs
└── Resource exhaustion → Start with Metrics (memory/CPU)
└── kubectl describe → Logs for OOM context
Quick Access
Every query below goes through one wrapper, obs-query.sh, which ships next to this file:
bash "$NAV_PILOT_SKILLS_DIR/observability-debugging/obs-query.sh" --help
nav-pilot sets NAV_PILOT_SKILLS_DIR at launch to wherever it materialised these skills for the client you are running, which differs per client, so use the variable rather than a literal path. bash, because a skill's files install without the executable bit.
Why a wrapper rather than a hand-written curl: these four hosts sit behind two cplt gates and a Mimir tenant header, and each refuses a request differently. Piped into jq, every one of them arrives as parse error: Invalid numeric literal, which reads like a broken query. The wrapper reads the status code, keeps a refusal off stdout, and names the rule that stopped the request. Only a 2xx body reaches stdout, so | jq . is always safe.
What ships with it
3 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.
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.
- 1mo ago Changed · +25 lines 72190d7c7633
- 1mo ago Changed · +16 lines c62efb720e1f
- 1mo ago First seen · 309 lines · 38 tokens per session scan A bf5661705b6d
observability-debugging is a skill published in the GitHub repository navikt/copilot (56 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 4,700 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
agents-sdk-typescript-debugging
Use when troubleshooting an agent built with the Microsoft Agents SDK (@microsoft/agents-hosting and related packages). Trigger on any of these symptoms: build or TypeScript errors, crashes on startup, 401 or auth errors on incoming requests, the bot not responding to messages, .env configuration problems, Azure AD…
agents-sdk-dotnet-debugging
Use when troubleshooting an agent built with the Microsoft Agents SDK (Microsoft.Agents.Hosting.AspNetCore and related packages) in C# / .NET. Trigger on any of these symptoms: build or C# compile errors, crashes on startup, 401 or auth errors on incoming requests, the bot not responding to messages, appsettings.json…
workers-profiling
Profile or debug CPU usage and memory allocation in deployed Cloudflare Workers and Durable Objects. Then use this information to optimize your code.
windbg-diagnostic-method
Use with every WinDbg plugin investigation to apply evidence-first reasoning, confidence calibration, contrarian review, structured reporting, and deterministic validation. Not a bug-family-specific triage skill.
windbg-kernel-bugcheck-triage
Use when a kernel dump reports a Windows bugcheck; decode parameters and recover exception or trap context before investigating your driver. Not for user-mode process crashes or blaming a module from its name alone.
windbg-user-exception-triage
Use when a native C/C++ app, service, or user-mode driver host (including UMDF) crashes with a structured exception in a dump or WinDbg session, including native faults inside managed processes. Not for managed .NET exceptions, WinUI/XAML app errors, or kernel bugchecks.