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-env-syncgit 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-env-sync)<a href="https://agentmods.dev/skills/dotlas/skills/vercel-env-sync"><img src="https://agentmods.dev/badge/skills/dotlas/skills/vercel-env-sync/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-env-sync"><img src="https://agentmods.dev/badge/skills/dotlas/skills/vercel-env-sync.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 | $0.00084 | $0.02581 |
| Opus 5.5 | $0.00034 | $0.01032 |
| Sonnet 5.5 | $0.00017 | $0.00516 |
| Haiku 4.5 | $0.00008 | $0.00258 |
Grade A, and why
vercel-env-sync 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vercel Env Sync
Safety
Non-negotiable:
- NEVER run
vercel deploy,vercel rollback,vercel alias,vercel domains <mut>,vercel project rm, or any deploy / domain / project mutation. Production deploys belong to the GitHub integration onmain. If the user asks for a deploy, refuse and redirect togit push. - NEVER run
vercel linkorvercel env pullwithout first checkinggit diff .env.local. Both commands overwrite that file. If it’s dirty, back it up (cp .env.local .env.local.bak) and tell the user before proceeding. - NEVER run
vercel env rmwithout explicit per-variable, per-environment user sign-off. Removal is destructive (no undo, no version history). Present the list, wait for the user to name each var in their approval, then execute one at a time. - NEVER print secret values to the transcript. Echo
${#VAR}(length) or first/last 4 chars only. Treat anything in.env.localas production-grade credentials. - NEVER set Vercel-injected vars (
VERCEL_URL,VERCEL_PROJECT_PRODUCTION_URL,VERCEL_ENV,VERCEL_GIT_COMMIT_SHA,VERCEL_REGION, …). If you find one set as a project env var, flag it — the dashboard value overrides Vercel’s runtime injection and will silently break URL resolution. - NEVER add a
NEXT_PUBLIC_*mirror of a server-only secret (CRON_SECRET,VERCEL_AUTOMATION_BYPASS_SECRET, database URLs, API keys). These leak to the browser bundle. - Vercel CLI is not signed-in by default in CI. If
vercel whoamifails, stop and tell the user — do not try to log in non-interactively.
Discovery
Replace <your-scope> and <your-vercel-project> with the values in
<app>/.vercel/project.json. If your project keeps a Vercel conventions doc, read it
before doing anything non-trivial.
All vercel commands must be detached from stdin (< /dev/null) or they hang in
agent shells.
# Auth + scope
pnpm exec vercel whoami < /dev/null
pnpm exec vercel teams ls < /dev/null 2>&1 | cat
# Confirm the link is correct
cat <app>/.vercel/project.json 2>/dev/null \
|| echo "NOT LINKED — run: cd <app> && pnpm exec vercel link --yes --scope <your-scope> --project <your-vercel-project>"
# Project facts
cd <app> && pnpm exec vercel project inspect <your-vercel-project> --scope <your-scope> < /dev/null 2>&1 | cat
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 · 223 lines · 84 tokens per session scan A db4a5fe90c55
vercel-env-sync is a skill published in the GitHub repository dotlas/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 2,581 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
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
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…
application-design-center-design-deploy
Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting…
gke-alert-configuration
Configures alerting policies in Terraform for Google Kubernetes Engine (GKE) clusters, workloads, and services using PromQL and Google Cloud Managed Service for Prometheus. Use when writing, analyzing, validating, or deploying Terraform alerting policies to monitor GKE service latency, traffic, error rates using…
google-cloud-storage-basics
Stores, retrieves, and manages data as objects in Cloud Storage on Google Cloud (also known colloquially as GCS) buckets. Use when you need to interact with Cloud Storage — set up a Storage MCP server (remote or local Toolbox), create or configure buckets, upload, download, stream, or transfer data, organize objects…
gke-ai-troubleshooting-tpu-partition-overlap
Diagnose and resolve GKE TPU slice creation failures (SliceCreationFailed) caused by partition overlap conflicts where requested TPU partitions or their nodes are already used by another slice or JobSet. Use when diagnosing GKE TPU slice creation failures with SliceCreationFailed partition or node conflicts. Don't use…