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 skills/nebari-dev/pi-coding-agent-pack/observabilitynpx skills add nebari-dev/pi-coding-agent-pack --skill observabilitygit clone --depth 1 https://github.com/nebari-dev/pi-coding-agent-packWhat 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 | $0.00046 | $0.01422 |
| Opus 5 | $0.00023 | $0.00711 |
| Sonnet 5 | $0.00009 | $0.00284 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
observability scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS "${GRAFANA_SVC}/login" >/dev/null && echo grafana_ok How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observability Skill (Nebari + Generic Kubernetes)
Use this skill whenever the user asks to:
- debug deployments using logs/events/rollout state,
- verify monitoring is working,
- find Grafana/Loki/Prometheus/Mimir/Tempo endpoints,
- check whether Pi users can access observability data.
This skill supports:
- local k3s/k3d,
- cloud Kubernetes (EKS/GKE/AKS),
- generic Kubernetes environments.
Core design awareness (important)
In Nebari Pi environments, the common architecture is:
- Pi/JupyterHub workloads in an app namespace (often
data-science), - LGTM stack in
monitoring, - optional
pi-observability-proxyandpi-debugCLI for curated debugging.
Access paths you must evaluate
- pi-debug path (if available):
pi-debug logs|events|rollout|doctor- Usually fronted by
pi-observability-proxy.
- Direct in-cluster LGTM path:
- Loki/Mimir/Tempo/Grafana service DNS from within Pi pod.
- Port-forward/browser path:
- useful when running from local workstation or when pod egress is restricted.
Do not assume only one path exists. Detect and use what works.
Workflow
0) Detect environment + tools
Run:
kubectl config current-context
kubectl get ns
Then detect whether pi-debug exists:
command -v pi-debug >/dev/null && echo "pi-debug available" || echo "pi-debug not available"
If pi-debug is available, test quickly:
pi-debug doctor --app pi || true
1) Discover LGTM endpoints (do not hardcode)
Preferred discovery:
kubectl get svc -A | grep -Ei 'grafana|loki|mimir|tempo|prometheus'
Export discovered endpoints (examples):
export GRAFANA_SVC="http://<grafana-svc>.<ns>.svc.cluster.local:80"
export LOKI_URL="http://<loki-svc>.<ns>.svc.cluster.local:3100"
export MIMIR_URL="http://<mimir-gateway-svc>.<ns>.svc.cluster.local"
export TEMPO_URL="http://<tempo-svc>.<ns>.svc.cluster.local:3200"
export PROM_URL="http://<prometheus-svc>.<ns>.svc.cluster.local:9090"
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 · 194 lines · 46 tokens per session scan A 7a3223042233
observability is a skill published in the GitHub repository nebari-dev/pi-coding-agent-pack (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,422 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
application-design-center-design-deploy
Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting…
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
huggingface-spaces
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't…
yandex-cloud
Read Yandex Cloud through its REST API. Applies to any question about VMs, metrics, logs, audit events, Kubernetes, managed databases, serverless, networking or any other Yandex Cloud resource. Never shell out to the yc CLI — it is not how this agent reaches Yandex Cloud and is usually not installed.
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…