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 aiappsgbb/awesome-gbb --skill foundry-network-runbookgit clone --depth 1 https://github.com/aiappsgbb/awesome-gbbWrote 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/aiappsgbb/awesome-gbb/foundry-network-runbook)<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/foundry-network-runbook"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/foundry-network-runbook/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/aiappsgbb/awesome-gbb/foundry-network-runbook"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/foundry-network-runbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00236 | $0.06223 |
| Opus 5 | $0.00118 | $0.03112 |
| Sonnet 5 | $0.00047 | $0.01245 |
| Haiku 4.5 | $0.00024 | $0.00622 |
Grade A, and why
foundry-network-runbook 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundry Network Runbook — Diagnose connectivity failures after the deploy succeeds
1. Goal
This runbook is for the on-call engineer who just got the page "Foundry
agent is up but inference / project connection / model call is failing
over the network." The foundry-vnet-deploy succeeded (or the
foundry-caphost-lifecycle create returned Succeeded), the resources
exist in the portal — but something at the network layer is wrong:
DNS resolves to the wrong IP, an NSG drops the packet, an RBAC role is
missing for a private DNS zone, a VNet peering went Disconnected, the
caphost subnet is wedged. You have ≤ 30 minutes to isolate the layer
before escalating.
This runbook is not a telemetry guide (foundry-observability
covers App Insights + OTel wiring), not a deploy guide
(foundry-vnet-deploy covers Day-0; foundry-caphost-lifecycle covers
Day-2 lifecycle), not an auth / JWT troubleshoot for the Citadel APIM
gateway (that's citadel-spoke-onboarding), and not an SDK / quota
troubleshoot. If the symptom is not a network-layer symptom, jump to
§ 8 — the cross-reference index points you at the right skill.
2. When to use this runbook
Trigger this runbook when all of the following are true:
- The Foundry deployment (or hosted-agent create, or caphost create)
reported
Succeededin ARM and the resources are visible in the portal. - Something fails downstream at the network layer: 503 from inference,
DNS resolving to a public IP, project connection showing red, a
private endpoint missing or not approved, a fresh redeploy hitting
Subnet already in use. - You have a baseline of "this worked yesterday" or "the deploy just completed, why doesn't it work now?" — i.e., the failure mode is operational (post-deploy), not a code or SDK bug.
If the failure is during the Bicep az deployment group create itself,
use foundry-vnet-deploy § 10b (safe retry). If the failure is a
hosted-agent-creation 403 with MI provisioning failed or
NIC provisioning failed, this runbook's § 4 matrix points you back to
foundry-vnet-deploy § 8b for the RBAC fix.
What ships with it
2 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.
- 9d ago First seen · 383 lines · 236 tokens per session scan A 5d172bec0af0
foundry-network-runbook is a skill published in the GitHub repository aiappsgbb/awesome-gbb (5 stars, last pushed 2d ago), licensed MIT. It adds 236 tokens to every session and 6,223 once invoked, about $0.0012 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.
Other skills, from other repositories
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-workload-troubleshooting
Diagnoses GKE workload failures (CrashLoopBackOff, OOMKilled, ImagePullBackOff, Pending, etc.) via logs and events. Use when pods fail to start or crash repeatedly. Don't use for GKE cluster infrastructure provisioning, node pool creation, or non-Kubernetes Google Cloud services.
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-handle-disruption-gpu-tpu
Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when diagnosing node disruptions, predicting host maintenance events on GPU/TPU nodepools, inspecting node interruption PromQL metrics, auditing…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.