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 Kilo-Org/kilo-marketplace --skill glue-diagnosticsgit clone --depth 1 https://github.com/Kilo-Org/kilo-marketplaceWrote 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/kilo-org/kilo-marketplace/glue-diagnostics)<a href="https://agentmods.dev/skills/kilo-org/kilo-marketplace/glue-diagnostics"><img src="https://agentmods.dev/badge/skills/kilo-org/kilo-marketplace/glue-diagnostics/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/kilo-org/kilo-marketplace/glue-diagnostics"><img src="https://agentmods.dev/badge/skills/kilo-org/kilo-marketplace/glue-diagnostics.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 | $0.00152 | $0.02012 |
| Opus 5 | $0.00076 | $0.01006 |
| Sonnet 5 | $0.00030 | $0.00402 |
| Haiku 4.5 | $0.00015 | $0.00201 |
Grade A, and why
glue-diagnostics 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Glue Diagnostics
When to use
Any AWS Glue investigation where the console alone is insufficient — job failures, OOM errors, Spark crashes, crawler schema misdetection, connection timeouts, Data Catalog drift, DPU under/over-provisioning, data skew, bookmark corruption, or Glue Studio generation errors.
Investigation workflow
Step 1 — Collect and triage
aws glue get-job --name <job-name>
aws glue get-job-run --job-name <job-name> --run-id <run-id>
aws glue batch-get-jobs --job-names <job1> <job2>
aws glue get-crawler --name <crawler-name>
aws glue get-connection --name <connection-name>
aws logs filter-log-events --log-group-name /aws-glue/jobs/logs-v2 --log-stream-name-prefix <run-id>
Step 2 — Domain deep dive
aws glue get-job-runs --job-name <job-name> --max-results 10
aws glue get-crawler-metrics --crawler-name-list <crawler-name>
aws glue get-databases
aws glue get-tables --database-name <db-name>
aws glue get-partitions --database-name <db-name> --table-name <table-name>
aws glue get-job-bookmark --job-name <job-name>
aws cloudwatch get-metric-statistics --namespace Glue --metric-name glue.driver.aggregate.bytesRead --dimensions Name=JobName,Value=<job-name> --start-time <iso> --end-time <iso> --period 300 --statistics Sum
Read references/glue-guardrails.md before concluding on any Glue issue.
Tool quick reference
| Tool / API | When to use |
|---|---|
glue get-job |
Job configuration, Glue version, DPU, worker type |
glue get-job-run |
Specific run status, error message, execution time |
glue batch-get-jobs |
Retrieve multiple job configs at once |
glue get-job-runs |
Job run history, failure patterns |
glue get-crawler |
Crawler config, targets, schedule, schema change policy |
glue get-crawler-metrics |
Crawler runtime stats, tables created/updated |
glue get-connection |
JDBC/network connection config, VPC, subnet |
glue get-databases / get-tables |
Data Catalog metadata, schema definitions |
glue get-partitions |
Partition metadata, partition keys, storage location |
glue get-job-bookmark |
Bookmark state for incremental processing |
logs filter-log-events |
Glue job CloudWatch logs for Spark errors |
cloudwatch get-metric-statistics |
Glue job metrics (bytes read/written, DPU usage) |
What ships with it
27 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.
- LICENSE 946 B
- README.md 3.3 KB
- references/A1-job-failures.md 5.4 KB
- references/A2-job-timeout.md 5.5 KB
- references/A3-oom-errors.md 5.7 KB
- references/A4-spark-errors.md 5.4 KB
- references/B1-crawler-failures.md 5.1 KB
- references/B2-schema-detection.md 5.4 KB
- references/B3-partition-issues.md 5.5 KB
- references/C1-jdbc-connection-failures.md 5.7 KB
- references/C2-vpc-subnet-issues.md 5.7 KB
- references/C3-s3-endpoint-access.md 5.5 KB
- references/D1-catalog-sync-issues.md 5.6 KB
- references/D2-schema-evolution.md 5.6 KB
- references/E1-dpu-sizing.md 5.4 KB
- references/E2-shuffle-issues.md 5.3 KB
- references/E3-data-skew.md 5.3 KB
- references/F1-transformation-errors.md 5.6 KB
- references/F2-bookmark-issues.md 5.8 KB
- references/F3-data-quality.md 5.5 KB
- references/G1-iam-permissions.md 5.6 KB
- references/G2-encryption-issues.md 5.6 KB
- references/glue-guardrails.md 4.6 KB
- references/glue-hallucination-patterns.yaml 7.5 KB
- references/H1-visual-editor-errors.md 5.3 KB
- references/H2-job-generation.md 5.5 KB
- references/Z1-general-troubleshooting.md 5.7 KB
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 · 136 lines · 152 tokens per session scan A f912073941de
glue-diagnostics is a skill published in the GitHub repository Kilo-Org/kilo-marketplace (175 stars, last pushed 22d ago), licensed Apache-2.0. It adds 152 tokens to every session and 2,012 once invoked, about $0.0008 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 2026-09-03.
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.