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 tomzx/agents --skill observe-productiongit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/observe-production)<a href="https://agentmods.dev/skills/tomzx/agents/observe-production"><img src="https://agentmods.dev/badge/skills/tomzx/agents/observe-production/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/tomzx/agents/observe-production"><img src="https://agentmods.dev/badge/skills/tomzx/agents/observe-production.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00023 | $0.01233 |
| Opus 5 | $0.00012 | $0.00616 |
| Sonnet 5 | $0.00005 | $0.00247 |
| Haiku 4.5 | $0.00002 | $0.00123 |
Grade A, and why
observe-production 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 5d 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 <metrics-endpoint>/api/v1/query?query=rate(http_requests_total[5m])` | Query Prometheus for request rate | How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observe Production
Checks the health of a deployed service or feature by reviewing SLOs, error rates, latency, throughput, and recent alerts. Produces a health report suitable for maintenance reviews, post-deploy verification, or incident triage.
Prerequisites
- Access to observability tooling (logs, metrics, tracing) via CLI, API, or dashboards
- Optional:
$1— service name or feature slug to scope the check (defaults to the whole project) - Read
.sdlc/context/architecture.mdto understand which services and infrastructure to check
What This Skill Checks
| Signal | Source | What It Reveals |
|---|---|---|
| Error rate | Metrics / logs | Increase in 4xx/5xx responses, unhandled exceptions |
| Latency (p50, p95, p99) | Metrics | Performance degradation, slow queries, bottlenecks |
| Throughput | Metrics | Traffic anomalies, load spikes, capacity issues |
| SLO status | SLO dashboard / config | Whether reliability targets are being met |
| Recent alerts | Alerting system | Active or recent incidents, degraded conditions |
| Deployment recency | CI/CD history | Whether a recent deploy correlates with issues |
Steps
-
Read
.sdlc/context/architecture.mdto identify services, endpoints, and infrastructure to check. -
Determine available observability tooling. Look for:
- Metrics: Prometheus, Datadog, CloudWatch, Grafana
- Logging: ELK, Loki, CloudWatch Logs
- Tracing: Jaeger, Zipkin, Datadog APM
- Alerting: PagerDuty, OpsGenie, Grafana alerts
If no tooling is configured, report that observability is not set up and recommend
/audit-observability.
-
Check error rates for the target service(s):
- HTTP 5xx rate over the last 1 hour, 24 hours, and 7 days
- Unhandled exception count
- Compare against baseline or SLO target
-
Check latency percentiles:
- p50, p95, p99 for the primary endpoints
- Compare against SLO targets or historical baseline
- Identify any slow endpoints
-
Check throughput:
- Requests per second over the last hour
- Compare against capacity limits or historical norms
- Identify any traffic anomalies
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.
- 5d ago First seen · 148 lines · 23 tokens per session scan A 4219eee1afd5
observe-production is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,233 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 2026-09-03.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
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…