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 divinevideo/divine-mobile --skill fastly-multi-service-routing-debuggit clone --depth 1 https://github.com/divinevideo/divine-mobileWrote 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/divinevideo/divine-mobile/fastly-multi-service-routing-debug)<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/fastly-multi-service-routing-debug"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/fastly-multi-service-routing-debug/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/divinevideo/divine-mobile/fastly-multi-service-routing-debug"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/fastly-multi-service-routing-debug.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 | $0.00101 | $0.01231 |
| Opus 5 | $0.00051 | $0.00616 |
| Sonnet 5 | $0.00020 | $0.00246 |
| Haiku 4.5 | $0.00010 | $0.00123 |
Grade A, and why
fastly-multi-service-routing-debug scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sI -H "Cache-Control: no-cache" "https://subdomain.your-domain.com/?t=$(date +%s)" How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fastly Multi-Service Routing Debug
Problem
You deploy changes to a Fastly Compute service but the behavior doesn't change. Requests still return old responses, redirects, or errors even after:
- Deploying new code with
fastly compute publish - Purging the cache with
fastly purge --all - Verifying the correct service version is active
Context / Trigger Conditions
- DNS resolves to Fastly IPs (151.101.x.x)
- Response headers show
x-served-by: cache-xxx(Fastly cache) - Deployed code should return different status/headers but doesn't
- Multiple Fastly services exist for the same project (e.g.,
divine-web,divine-router) - Wildcard subdomain routing is involved (*.example.com)
Solution
Step 1: Identify Which Service Handles the Domain
# List all services
fastly service list
# Check which service handles your domain using domain-v1
fastly domain-v1 list | grep your-domain.com
The output shows the service ID for each domain:
*.divine.video glh3AfBEmZKzmAmByvGyAg 76fTayX6mBKa8faLeZ1fet 2025-12-28...
divine.video 1JttvGPc6AlOVg4koUGhPg 76fTayX6mBKa8faLeZ1fet 2025-11-23...
The third column is the service ID that handles that domain.
Step 2: Verify Service Architecture
Common patterns:
- Router + Content: A routing service (often Rust) sits in front, handling subdomain logic, then passes through to a content service
- Gateway Pattern: Edge gateway handles auth/rate-limiting, then proxies to origin
- Wildcard Routing:
*.domain.commay be handled by a different service thandomain.com
Step 3: Debug the Correct Service
Once you identify the routing service:
# Check its active version
fastly service-version list --service-id <router-service-id>
# Check its domains
fastly domain list --service-id <router-service-id> --version active
# Find and read its source code (usually in a different repo)
Step 4: Trace Request Flow
Add debug logging to understand the flow:
- In the routing service: log the Host header and routing decision
- In the content service: log if requests are even reaching it
- Check Fastly logs:
fastly log-tail --service-id <id>
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.
- 10d ago First seen · 141 lines · 101 tokens per session scan A c1878aa284b4
fastly-multi-service-routing-debug is a skill published in the GitHub repository divinevideo/divine-mobile (265 stars, last pushed today), licensed MPL-2.0. It adds 101 tokens to every session and 1,231 once invoked, about $0.0005 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 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.