Vercel Eve
magnus919/agent-skills
Build, develop, deploy, self-host, secure, and troubleshoot durable backend AI agents with Vercel Eve.
Vercel AI Gateway guidance for setup, model discovery, authentication, routing, fallbacks, virtual models, evaluation models, BYOK, budgets, spend reporting, observability, compatible APIs, and…
Install AI Gateway
$ npx skills add vercel/vercel-plugin --skill ai-gateway -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install vercel/vercel-plugin ai-gateway --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/vercel/vercel-plugin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-gateway .claude/skills/ai-gateway && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ai-gateway" agent skill from https://github.com/vercel/vercel-plugin/tree/main/skills/ai-gateway into .claude/skills/ai-gateway/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-gateway", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/vercel/vercel-plugin/tree/main/skills/ai-gatewayType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add vercel/vercel-plugin --skill ai-gateway -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install vercel/vercel-plugin ai-gateway --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vercel/vercel-plugin.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ai-gateway .agents/skills/ai-gateway && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ai-gateway" agent skill from https://github.com/vercel/vercel-plugin/tree/main/skills/ai-gateway into .agents/skills/ai-gateway/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-gateway", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add vercel/vercel-plugin --skill ai-gateway -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install vercel/vercel-plugin ai-gateway --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vercel/vercel-plugin.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ai-gateway .cursor/skills/ai-gateway && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ai-gateway" agent skill from https://github.com/vercel/vercel-plugin/tree/main/skills/ai-gateway into .cursor/skills/ai-gateway/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-gateway", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/vercel/vercel-plugin.git --path skills/ai-gateway--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add vercel/vercel-plugin --skill ai-gateway -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install vercel/vercel-plugin ai-gateway --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vercel/vercel-plugin.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ai-gateway .gemini/skills/ai-gateway && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ai-gateway" agent skill from https://github.com/vercel/vercel-plugin/tree/main/skills/ai-gateway into .gemini/skills/ai-gateway/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-gateway", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install vercel/vercel-plugin ai-gatewayInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add vercel/vercel-plugin --skill ai-gateway -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/vercel/vercel-plugin.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ai-gateway .github/skills/ai-gateway && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ai-gateway" agent skill from https://github.com/vercel/vercel-plugin/tree/main/skills/ai-gateway into .github/skills/ai-gateway/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-gateway", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add vercel/vercel-plugin --skill ai-gateway -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install vercel/vercel-plugin ai-gateway --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vercel/vercel-plugin.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ai-gateway .opencode/skills/ai-gateway && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ai-gateway" agent skill from https://github.com/vercel/vercel-plugin/tree/main/skills/ai-gateway into .opencode/skills/ai-gateway/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-gateway", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ai-gateway- GitHub stars
- 301
- Token cost
- ~4.4k tokens
- SKILL.md length
- 1,430 words
- Files
- 8 (incl. references)
- Skills in repo
- 38
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Vercel AI Gateway guidance for setup, model discovery, authentication, routing, fallbacks, virtual models, evaluation models, BYOK, budgets, spend reporting, observability, compatible APIs, and…
- Works in 5 steps: Inspect the project's language, package… → Read the relevant Vercel page under .… → Fetch the complete live model list. Do… → …
- Adding AI Gateway to an app
- SKILL.md covers Start with current sources, Vercel CLI inventory, Route the request to the right… and Choose the integration surface, plus 6 more sections
- Calls vercel and curl; reaches ai-gateway.vercel.sh; needs AI_GATEWAY_API_KEY and VERCEL_OIDC_TOKEN
What it does
AI Gateway is an agent skill from vercel/vercel-plugin, published by the product's own GitHub organization. Vercel AI Gateway guidance for setup, model discovery, authentication, routing, fallbacks, virtual models, evaluation models, BYOK, budgets, spend reporting, observability, compatible APIs, and coding-agent configuration. Use when adding AI Gateway to an app, migrating provider calls, choosing models or providers, centralizing model configuration, evaluating application state, debugging gateway requests, or running vercel ai-gateway commands.
Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/coding-agents.md`, `references/evaluation.md` and `references/routing.md`).
It sits in DevOps & Cloud, covering Observability. It works with Vercel and Vercel AI SDK. The repository describes itself as: Comprehensive Vercel ecosystem plugin — relational knowledge graph, skills for every major product, specialized agents, and Vercel conventions. Turns any AI agent into a Vercel…
When your agent uses it
- Adding AI Gateway to an app
- Migrating provider calls
- Choosing models
- Centralizing model configuration
Example prompts
- “/ai-gateway”
Requirements
- Python 3
- Node.js
- A credential in OPENAI_API_KEY
- A credential in ANTHROPIC_API_KEY
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Inspect the project's language, package manager, installed AI SDK version, and existing provider integration.
- Read the relevant Vercel page under . Use the page's .md form when a tool needs Markdown.
- Fetch the complete live model list. Do not construct model variants by analogy
- If the code uses the ai package, load the ai-sdk skill when available. Read version-matched docs under node_modules/ai/docs/ and source…
- Run vercel ai-gateway --help before documenting or scripting CLI flags.
What it can do on your machine
Read from SKILL.md and the folder at commit 2a1e58d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
vercelcurl
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
ai-gateway.vercel.sh
Also links to:
vercel.comai-sdk.dev
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
AI_GATEWAY_API_KEYVERCEL_OIDC_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
AI Gateway loads about 4.4k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 115 tokens; SKILL.md has 1,430 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:235
e.js script does not automatically load `.env.local`. Export variables in the shell or load that file explicitly. Framew - NoteMentions a .env fileSKILL.md:271
works in the actual runtime, including `.env.local` loading where relevant.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,430 words (~4,386 tokens).
“AI Gateway exposes models from multiple providers through shared authentication, model IDs, routing, billing, and observability. Model availability, SDK APIs, CLI commands, prices, and product capabilities change frequently. Verify them from current sources before changing code.”
- name
- ai-gateway
- summary
- Set up and operate Vercel AI Gateway with current models, virtual models, evaluation, authentication, routing, spend controls, and verification.
- metadata.priority
- 7
- metadata.docs
- https://vercel.com/docs/ai-gateway, https://vercel.com/docs/ai-gateway/getting-started, https://vercel.com/docs/ai-gateway/models-and-providers/virtual-models…
- metadata.sitemap
- https://vercel.com/docs/sitemap.md
- metadata.importPatterns
- ai, @ai-sdk/gateway
- metadata.bashPatterns
- \bvercel\s+ai-gateway\b, \bvercel\s+env\s+pull\b, \bnpm\s+(install|i|add)\s+[^\n]*@ai-sdk/gateway\b, \bpnpm\s+(install|i|add)\s+[^\n]*@ai-sdk/gateway\b…
- retrieval.aliases
- model router, ai proxy, provider failover, llm gateway, gateway credits, virtual model, evaluation model, typesafe compatibility
- retrieval.intents
- add Vercel AI Gateway to an application, route AI models across providers, configure provider or model fallbacks, authenticate AI Gateway requests, track AI…
- retrieval.entities
- AI Gateway, AI Gateway Credits, providerOptions.gateway, AI_GATEWAY_API_KEY, VERCEL_OIDC_TOKEN, model routing, provider failover, BYOK, spend reporting…
Files
SKILL.md and 7 other files (references) in skills/ai-gateway of vercel/vercel-plugin.
- SKILL.md
- .vercel.approvers
- references/coding-agents.md
- references/evaluation.md
- references/routing.md
- references/setup.md
- references/spend-observability.md
- references/virtual-models.md
Open the folder on GitHubat commit 2a1e58d
Compare with similar skills
AI Gateway next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| AI Gateway this skillvercel/vercel-plugin | 301 | — | ~4.4k | Automated safety check: Notes | Custom licence | |
| Vercel Evemagnus919/agent-skills | 116 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Frontmcp Production Readinessagentfront/frontmcp | 146 | — | ~6.5k | Automated safety check: Pass | Apache-2.0 | |
| Ecosystem Usageevloghq/evlog | 1.9k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Groq Deploy Integrationjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Vercel Observabilityjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~2k | Automated safety check: Pass | MIT |
Similar skills
Frontmcp Production Readiness
agentfront/frontmcp
Pre-production audit, hardening, and go-live checklists for FrontMCP servers.
Ecosystem Usage
evloghq/evlog
Measure agent-facing traffic to the evlog docs site (MCP transport, raw Markdown, discovery paths) with Vercel Observability, and read it without inflating it.
Groq Deploy Integration
jeremylongshore/tons-of-skills-marketplace
Deploy Groq integrations to Vercel, Cloud Run, and containerized platforms.
Vercel Observability
jeremylongshore/tons-of-skills-marketplace
Set up Vercel observability with runtime logs, analytics, log drains, and OpenTelemetry tracing.
- Official
Vercel Optimize Audit
vercel-labs/agent-skills
Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.
More from vercel/vercel-plugin
All 38 skills in this repo- Official
Deployments Cicd
vercel/vercel-plugin
Vercel deployment and CI/CD expert guidance. An agent skill from vercel/vercel-plugin.
- Official
Plugin Audit
vercel/vercel-plugin
Audit vercel-plugin performance on real-world projects. An agent skill from vercel/vercel-plugin.
- Official
Vercel CLI
vercel/vercel-plugin
Vercel CLI expert guidance. An agent skill from vercel/vercel-plugin.
- Official
Vercel Services
vercel/vercel-plugin
Configure and troubleshoot Vercel Services for multiple frontends and backends in one project.
- Official
Access Protected Vercel Deployment
vercel/vercel-plugin
Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection.
- Official
Bootstrap
vercel/vercel-plugin
Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations).
Related
Works with
Categories
Questions about AI Gateway
What does AI Gateway do?
Vercel AI Gateway guidance for setup, model discovery, authentication, routing, fallbacks, virtual models, evaluation models, BYOK, budgets, spend reporting, observability, compatible APIs, and…. AI Gateway is an agent skill from vercel/vercel-plugin, published by the product's own GitHub organization. Vercel AI Gateway guidance for setup, model discovery, authentication, routing, fallbacks, virtual models, evaluation models, BYOK, budgets, spend reporting, observability, compatible APIs, and coding-agent configuration.
When should I use AI Gateway?
AI Gateway fits situations like: adding AI Gateway to an app; migrating provider calls; choosing models; centralizing model configuration.
How do I install AI Gateway in Claude Code?
Run `npx skills add vercel/vercel-plugin --skill ai-gateway -a claude-code`. Or copy the skill folder (skills/ai-gateway in vercel/vercel-plugin) into .claude/skills/ai-gateway in your project. Claude Code loads it when a task matches its description.
How do I install AI Gateway in Codex?
Run `npx skills add vercel/vercel-plugin --skill ai-gateway -a codex`. Or copy the skill folder (skills/ai-gateway in vercel/vercel-plugin) into .agents/skills/ai-gateway in your project. Codex loads it when a task matches its description.
Can I use AI Gateway in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vercel/vercel-plugin --skill ai-gateway -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-gateway, .gemini/skills/ai-gateway, .github/skills/ai-gateway and .opencode/skills/ai-gateway in your project.
What does AI Gateway need to run?
Going by SKILL.md and its folder, AI Gateway needs the command-line tools its instructions call (vercel and curl) and credentials named AI_GATEWAY_API_KEY and VERCEL_OIDC_TOKEN. Our summary lists: Python 3; Node.js; A credential in OPENAI_API_KEY; A credential in ANTHROPIC_API_KEY.
Does AI Gateway access the network?
SKILL.md names 3 domains. In commands or code: ai-gateway.vercel.sh; the agent is likely to contact it when it follows the instructions. As links in the text: vercel.com and ai-sdk.dev. This is read from the text; nothing was executed.
Is AI Gateway safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does AI Gateway use?
AI Gateway has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does AI Gateway use?
About 4.4k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 12k tokens, read only when the agent opens those files.
What are the alternatives to AI Gateway?
Skills that share tags, products or a category with AI Gateway: Vercel Eve (magnus919/agent-skills, 116 stars), Frontmcp Production Readiness (agentfront/frontmcp, 146 stars), Ecosystem Usage (evloghq/evlog, 1.9k stars) and Groq Deploy Integration (jeremylongshore/tons-of-skills-marketplace, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains AI Gateway?
vercel (a GitHub organization, an official publisher) maintains it in vercel/vercel-plugin, which has 301 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 8, 2026.
Source: vercel/vercel-plugin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.