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 dotlas/skills --skill vercel-logsgit clone --depth 1 https://github.com/dotlas/skillsWrote 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/dotlas/skills/vercel-logs)<a href="https://agentmods.dev/skills/dotlas/skills/vercel-logs"><img src="https://agentmods.dev/badge/skills/dotlas/skills/vercel-logs/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/dotlas/skills/vercel-logs"><img src="https://agentmods.dev/badge/skills/dotlas/skills/vercel-logs.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 | $0.00064 | $0.01704 |
| Opus 5.5 | $0.00026 | $0.00682 |
| Sonnet 5.5 | $0.00013 | $0.00341 |
| Haiku 4.5 | $0.00006 | $0.00170 |
Grade A, and why
vercel-logs 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 1mo 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vercel Logs
Safety
- Read-only. NEVER run
vercel deploy,vercel rollback,vercel alias,vercel env add/rm,vercel project rm, or any mutation. This skill only reads logs. - NEVER print secrets from log output. If a log line contains env var values, API keys, or tokens, redact before presenting.
- Use
--no-branchalways. The CLI auto-detects the local git branch and silently filters to it — wrong for production debugging. Always pass--no-branchor--environment productionexplicitly. - Detach stdin. Append
< /dev/nullto everyvercelcommand. Without it the CLI sniffs the TTY and hangs in agent shells. - Bound output. Always pass
--limit N(default 20, max 100). For--followruns, cap the observation window and kill the terminal when done — do not follow indefinitely.
Prerequisites
cd <repo-root>/<app>
pnpm exec vercel whoami < /dev/null 2>&1
cat .vercel/project.json 2>/dev/null | grep -o '"projectId":"[^"]*"'
If whoami fails → stop, tell user to run pnpm exec vercel login. If
.vercel/project.json is missing → run:
cd <app> && pnpm exec vercel link --yes --scope <your-scope> --project <your-vercel-project>
Retention: Hobby = 1h · Pro = 24h · Pro + Observability Plus = 30 days · Enterprise = 3 days. If the user asks for logs beyond the retention window, tell them and suggest checking external log drains if configured.
Query modes
Recent errors (default diagnostic)
The go-to when the user reports “something broke in prod”:
cd <repo-root>/<app> && \
pnpm exec vercel logs \
--no-branch \
--environment production \
--level error \
--since 1h \
--limit 20 \
--json \
--expand \
--no-follow \
< /dev/null 2>&1 | grep -E '^[{]' | jq .
Important: The CLI emits non-JSON preamble lines.
Always filter with grep -E '^[{]' before piping to jq. Use [{] not ^\{ — zsh
interprets bare braces.
Each line:
{
"id": "...",
"timestamp": 1779108733174,
"level": "error",
"message": "...",
"source": "serverless|edge-middleware|edge-function",
"requestMethod": "GET|POST",
"requestPath": "/api/...",
"responseStatusCode": 500,
"environment": "production",
"logs": [{ "level": "error", "message": "..." }] // with --expand
}
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.
- 1mo ago First seen · 200 lines · 64 tokens per session scan A fd153e41acd4
vercel-logs is a skill published in the GitHub repository dotlas/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 1,704 once invoked, about $0.0003 per session on Opus 5.5. 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-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-storage-troubleshooting
Diagnoses GKE persistent-storage failures — volume attach/mount errors (Regional PD on optimized VMs, fsGroup mount timeouts), disk-performance and node storage-pressure issues, slow-disk Pod-creation failures, volume-expansion problems, Local SSD / Hyperdisk Storage Pool creation errors, and Cloud Storage FUSE OOM.…
gke-workload-scaling-troubleshooting
Diagnoses GKE HorizontalPodAutoscaler (HPA) failures — metrics showing as , FailedGetResourceMetric / FailedGetScale / FailedComputeMetricsReplicas events, missing Pod resource requests, custom/external metrics-pipeline breakage (FailedGetExternalMetric / FailedGetCustomMetric, unavailable metrics adapter…
gke-ai-troubleshooting-tpu-mxla-hang
Diagnose GKE Cloud TPU multi-slice training hangs (Megascale HANGDETECTED logs and hang monitored events) using the ML Diagnostics Megascale XLA (MXLA) Hang Analyzer (gcloud alpha mldiagnostics monitored-events) and 1-minute Cloud Monitoring multi-slice latency metrics (kubernetes.io/container/multislice/).…
gke-ai-troubleshooting-tpu-performance-degradation
Diagnose GKE Cloud TPU training throughput drops and step-time regressions (15%+ TPU duty-cycle drop) using ML Diagnostics Workload Monitoring (gcloud alpha mldiagnostics monitored-events / hypercomputecluster.googleapis.com/v1alpha) and 1-minute Cloud Monitoring system metrics (kubernetes.io/node/accelerator/).…
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…