Agent skill

Vercel Eve

by magnus919 in magnus919/agent-skills

Build, develop, deploy, self-host, secure, and troubleshoot durable backend AI agents with Vercel Eve.

MITAuto-check passedDevOps & Cloud

Install Vercel Eve

skills CLI
$ npx skills add magnus919/agent-skills --skill vercel-eve -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install magnus919/agent-skills vercel-eve --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/vercel-eve .claude/skills/vercel-eve && rm -rf skills-src

Use ~/.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/

Facts

Skill name
vercel-eve
GitHub stars
115
Token cost
~1.9k tokens
SKILL.md length
821 words
Files
6 (incl. references)
Skills in repo
131
Repo updated
First seen
Licence
MIT

At a glance

Build, develop, deploy, self-host, secure, and troubleshoot durable backend AI agents with Vercel Eve.

  • Works in 5 steps: Start with the generated project… → Keep authority outside the model prompt.… → Treat a durable session as a workflow,… → …
  • Creating an Eve agent
  • SKILL.md covers Operating contract, When not to use, Project model and Quick start, plus 5 more sections
  • Calls npx, npm and vercel; needs AI_GATEWAY_API_KEY

What it does

Vercel Eve is an agent skill from magnus919/agent-skills. Build, develop, deploy, self-host, secure, and troubleshoot durable backend AI agents with Vercel Eve. Use when creating an Eve agent, adding tools, skills, subagents, channels, schedules, sandboxing, durable sessions, observability, or deploying Eve on Vercel or a Node host. Do not use for the separate Vercel AI SDK Agent APIs such as ToolLoopAgent or WorkflowAgent; use an AI SDK-specific skill for those.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `README.md`, `evals/evals.json` and `references/deployment-and-self-hosting.md`). Compatibility notes: Requires Node.js 24+ for the current Eve package. Deployment requires an LLM provider credential or Vercel AI Gateway access; self-hosted durable execution…

It sits in DevOps & Cloud, covering Observability and Subagents. It works with Vercel and Vercel AI SDK. The repository describes itself as: Curated collection of AI agent skills for Hermes and other agent frameworks. The licence is MIT.

When your agent uses it

  • Creating an Eve agent
  • Durable sessions
  • Deploying Eve on Vercel
  • The separate Vercel AI SDK Agent APIs such as ToolLoopAgent

Example prompts

  • “/vercel-eve”

Requirements

  • Node.js
  • A credential in AI_GATEWAY_API_KEY
  • Compatibility (from SKILL.md): Requires Node.js 24+ for the current Eve package. Deployment requires an LLM provider credential or Vercel AI Gateway access; self-hosted durable execution requires persistent workflow storage.

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Start with the generated project structure. Put agent behavior in agent/instructions.md, runtime choices in agent/agent.ts, and one typed…
  2. Keep authority outside the model prompt. Use typed tools, connections, sandbox boundaries, and route authentication instead of placing…
  3. Treat a durable session as a workflow, not an in-memory chat. Define persistence, idempotency, callback reachability, and recovery before…
  4. On self-hosted deployments, replace every Vercel service deliberately. A Node process that starts is not evidence that workflow callbacks…
  5. Verify with a health request and a real authenticated session that exercises the workflow path. Never treat an HTTP 200 alone as a…

What it can do on your machine

Read from SKILL.md and the folder at commit 22b4723. 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:

    • npx
    • npm
    • vercel

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, npm and vercel, which can reach the network depending on how they are called.

    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_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires Node.js 24+ for the current Eve package. Deployment requires an LLM provider credential or Vercel AI Gateway access; self-hosted durable execution requires persistent workflow storage.

    From compatibility in the SKILL.md frontmatter.

Context cost

Vercel Eve loads about 1.9k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 821 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.9k

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 passed

The automated check found no risky patterns in SKILL.md.

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

The full file from magnus919/agent-skills at commit 22b4723, republished under its MIT licence (© magnus919). 821 words, ~1,904 tokens.

Download SKILL.mdSave it as .claude/skills/vercel-eve/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
vercel-eve
description
Build, develop, deploy, self-host, secure, and troubleshoot durable backend AI agents with Vercel Eve. Use when creating an Eve agent, adding tools, skills, subagents, channels, schedules, sandboxing, durable sessions, observability, or deploying Eve on Vercel or a Node host. Do not use for the separate Vercel AI SDK Agent APIs such as ToolLoopAgent or WorkflowAgent; use an AI SDK-specific skill for those.
compatibility
Requires Node.js 24+ for the current Eve package. Deployment requires an LLM provider credential or Vercel AI Gateway access; self-hosted durable execution requires persistent workflow storage.
license
MIT
metadata.source
https://github.com/vercel/eve
metadata.research_checked
2026-07-15

Vercel Eve

Eve is a filesystem-first framework for durable backend agents. Treat the agent/ directory as the application boundary and the deployment as a composition of independently replaceable HTTP, workflow, sandbox, model, credential, and observability layers.

Operating contract

  1. Start with the generated project structure. Put agent behavior in agent/instructions.md, runtime choices in agent/agent.ts, and one typed capability per file under its relevant directory.
  2. Keep authority outside the model prompt. Use typed tools, connections, sandbox boundaries, and route authentication instead of placing credentials or policy in instructions.
  3. Treat a durable session as a workflow, not an in-memory chat. Define persistence, idempotency, callback reachability, and recovery before relying on long-running or side-effecting work.
  4. On self-hosted deployments, replace every Vercel service deliberately. A Node process that starts is not evidence that workflow callbacks, persisted state, schedules, sandbox isolation, authentication, and telemetry work.
  5. Verify with a health request and a real authenticated session that exercises the workflow path. Never treat an HTTP 200 alone as a production readiness signal.

When not to use

Do not load this for the separate ai package’s ToolLoopAgent, WorkflowAgent, or HarnessAgent APIs. Do not use it for generic Next.js deployment without an Eve agent. For vendor-neutral workflow orchestration, use the relevant workflow or agent-framework skill instead.

When such a request appears, say that Eve does not apply and route to current AI SDK documentation or an AI SDK-specific skill. Do not write AI SDK API code, model configuration, or deployment guidance from this skill.

Project model

NeedDefault location
Always-on behavioragent/instructions.md
Model and runtime optionsagent/agent.ts
Typed actionsagent/tools/*.ts
On-demand proceduresagent/skills/
Narrower child agentsagent/subagents/
HTTP, Slack, or other entry pointsagent/channels/
Typed external integrationsagent/connections/
Isolated computeagent/sandbox/
OpenTelemetry setupagent/instrumentation.ts
Recurring workagent/schedules/

Read development and architecture before creating or restructuring an agent.

Quick start

sh
npx eve@latest init my-agent
cd my-agent
npm run dev

Use the generated README and package scripts as the local source of truth. A minimal runtime configuration selects a model:

ts
import { defineAgent } from "eve";

export default defineAgent({
  model: "anthropic/claude-opus-4.8",
});

On Vercel, a string model ID routes through AI Gateway and can use project OIDC. Outside Vercel, either configure AI_GATEWAY_API_KEY or use an AI SDK provider object with the provider’s normal credential. Do not assume that BYOK means the Gateway is bypassed.

Build capabilities deliberately

Tools

A tool is a typed boundary between model reasoning and an external action. Give it a narrow schema and a description that makes the authorization and side-effect boundary clear. A tool declares typed inputs, outputs, and side effects. It does not hold credentials or grant authority: keep integration credentials in connections and enforce authorization server-side before the effect occurs.

ts
import { defineTool } from "eve/tools";
import { z } from "zod";

export default defineTool({
  description: "Look up a city’s current weather.",
  inputSchema: z.object({ city: z.string().min(1) }),
  async execute({ city }) {
    return { city, condition: "Sunny" };
  },
});

Use a skill for larger procedures that should load only when relevant. Use a subagent when the work needs a fresh history, narrower toolset, or isolated intermediate state.

Credentials and execution

Use agent/connections/ for typed service integrations. Use agent/sandbox/ for generated code or shell work. Never place provider keys, OAuth tokens, or route-auth secrets in instructions, tool source, generated artifacts, or logs.

For sandbox design and lifecycle choices, read development and architecture. For self-hosting backends and routing, read deployment and self-hosting.

Show full SKILL.md (310 more words)Show less

Deploy

Vercel

Use a Git-connected project or vercel deploy. Eve emits Vercel Build Output, uses Vercel Workflows for durable sessions, and normally selects Vercel Sandbox. Replace scaffolded placeholder authentication before exposing a browser-facing route.

Self-hosted Node service
sh
eve build
PORT=3000 eve start --host 0.0.0.0

This uses the normal Nitro Node output under .output/. Before production traffic, read deployment and self-hosting and explicitly verify persistent workflow storage, sandbox backend, model credential path, authentication, the /eve/ and /.well-known/workflow/ proxy prefixes, schedule execution, and telemetry.

Treat host paths, reverse-proxy product configuration, storage product, and scheduler implementation as target-specific evidence. If the target topology is not supplied or inspected, name the required contract and the missing evidence rather than inventing a configuration.

Security and observability

  • Replace placeholder authentication with a real policy before any production browser request. Outside Vercel, do not rely on vercelOidc() as the sole authenticator.
  • Give sandboxes the minimum network and credential access required. A sandbox does not protect secrets that are deliberately injected into it.
  • Vercel Agent Runs is convenient, but treat OpenTelemetry as the portable operational evidence path. Set recordInputs or recordOutputs to false when traces would contain sensitive data.
  • For personal, sensitive, or regulated data, assess what model inputs, tool arguments, outputs, and traces are retained and disclose collection where required.

Verification gate

  1. Build the deployed artifact.
  2. Confirm the health endpoint: GET /eve/v1/health.
  3. Start one authenticated session: POST /eve/v1/session.
  4. Attach to its stream and verify a real turn completes.
  5. For self-hosting, exercise a durable workflow callback or resume path, not only a stateless reply.
  6. Inspect the trace and ensure secrets and sensitive payloads are absent or intentionally redacted.

Exit criteria

The task is complete only when the requested agent capability is implemented, its route and authorization boundary are explicit, and the relevant local or deployed session path has been exercised with evidence. See source index when validating version-sensitive behavior.

© magnus919, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in vercel-eve of magnus919/agent-skills.

  • SKILL.md
  • README.md
  • evals/evals.json
  • references/deployment-and-self-hosting.md
  • references/development-and-architecture.md
  • references/source-index.md

Open the folder on GitHubat commit 22b4723

Compare with similar skills

Vercel Eve 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.

Vercel Eve compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vercel Eve this skillmagnus919/agent-skills115—~1.9kAutomated safety check: PassMIT
AI Gatewayvercel/vercel-plugin301—~4.4kAutomated safety check: NotesCustom licence
Marketplacevercel/vercel-plugin301—~2.3kAutomated safety check: PassCustom licence
Jevgrepdzhng/jevgrep2.5k—~741Automated safety check: PassMIT
Frontmcp Production Readinessagentfront/frontmcp146—~6.5kAutomated safety check: PassApache-2.0
Ecosystem Usageevloghq/evlog1.9k—~1.2kAutomated safety check: PassMIT

Similar skills

  • AI Gateway

    vercel/vercel-plugin

    Official

    Vercel AI Gateway guidance for setup, model discovery, authentication, routing, fallbacks, virtual models, evaluation models, BYOK, budgets, spend reporting, observability, compatible APIs, and…

    301 GitHub stars~4.4k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • Marketplace

    vercel/vercel-plugin

    Official

    Vercel Marketplace expert guidance — discovering, installing, and managing third-party integrations via the vercel integration CLI.

    301 GitHub stars~2.3k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Jevgrep

    dzhng/jevgrep

    A skill your agent uses for questions about how, why, or where behavior works in a repository, including questions that name a function or setting.

    2.5k GitHub stars~741 tokensUpdated 8 days ago
    DevelopmentAuto-check passed
  • Pre-production audit, hardening, and go-live checklists for FrontMCP servers.

    146 GitHub stars~6.5k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • 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.

    1.9k GitHub stars~1.2k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Groq Deploy Integration

    jeremylongshore/tons-of-skills-marketplace

    Deploy Groq integrations to Vercel, Cloud Run, and containerized platforms.

    2.8k GitHub stars~1.4k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from magnus919/agent-skills

All 131 skills in this repo
  • Artifact Pyramids

    magnus919/agent-skills

    Organize durable agent research outputs as summaries, analysis, and evidence dossiers.

    119 GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Ascii City Engine

    magnus919/agent-skills

    Build portable, first-person colored ASCII city engines and small GIS-derived city packs.

    119 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Color Management

    magnus919/agent-skills

    Manage color workflows with ICC profiles, working spaces, gamut mapping, and color science.

    119 GitHub stars~2.6k tokensUpdated today
    Auto-check: notes
  • Data Scientist

    magnus919/agent-skills

    A skill your agent uses for PhD-level expertise in data science, statistics, and machine learning: rigorous statistical analysis, experimental design, causal inference, advanced modeling, research…

    119 GitHub stars~4.1k tokensUpdated today
    Auto-check passed
  • Docker Compose

    magnus919/agent-skills

    Use Docker Compose to define, run, debug, and harden multi-container applications.

    119 GitHub stars~2k tokensUpdated today
    Auto-check: notes
  • Fpga Development

    magnus919/agent-skills

    Design, review, simulate, and verify FPGA logic using explicit RTL contracts, clock and reset models, CDC analysis, timing constraints, and reproducible implementation evidence.

    119 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

Categories

Questions about Vercel Eve

What does Vercel Eve do?

Build, develop, deploy, self-host, secure, and troubleshoot durable backend AI agents with Vercel Eve. Vercel Eve is an agent skill from magnus919/agent-skills. Build, develop, deploy, self-host, secure, and troubleshoot durable backend AI agents with Vercel Eve.

When should I use Vercel Eve?

Vercel Eve fits situations like: creating an Eve agent; durable sessions; deploying Eve on Vercel; the separate Vercel AI SDK Agent APIs such as ToolLoopAgent.

How do I install Vercel Eve in Claude Code?

Run `npx skills add magnus919/agent-skills --skill vercel-eve -a claude-code`. Or copy the skill folder (vercel-eve in magnus919/agent-skills) into .claude/skills/vercel-eve in your project. Claude Code loads it when a task matches its description.

How do I install Vercel Eve in Codex?

Run `npx skills add magnus919/agent-skills --skill vercel-eve -a codex`. Or copy the skill folder (vercel-eve in magnus919/agent-skills) into .agents/skills/vercel-eve in your project. Codex loads it when a task matches its description.

Can I use Vercel Eve 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 magnus919/agent-skills --skill vercel-eve -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vercel-eve, .gemini/skills/vercel-eve, .github/skills/vercel-eve and .opencode/skills/vercel-eve in your project.

What does Vercel Eve need to run?

Going by SKILL.md and its folder, Vercel Eve needs the command-line tools its instructions call (npx, npm and vercel) and credentials named AI_GATEWAY_API_KEY. Our summary lists: Node.js; A credential in AI_GATEWAY_API_KEY. Compatibility (from SKILL.md): Requires Node.js 24+ for the current Eve package. Deployment requires an LLM provider credential or Vercel AI Gateway access; self-hosted durable execution requires persistent workflow storage..

Does Vercel Eve access the network?

SKILL.md contains no URLs. Its commands use npx and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Vercel Eve safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vercel Eve use?

Vercel Eve is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vercel Eve use?

About 1.9k tokens (SKILL.md is roughly 7.6k 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 2k tokens, read only when the agent opens those files.

What are the alternatives to Vercel Eve?

Skills that share tags, products or a category with Vercel Eve: AI Gateway (vercel/vercel-plugin, 301 stars), Marketplace (vercel/vercel-plugin, 301 stars), Jevgrep (dzhng/jevgrep, 2.5k stars) and Frontmcp Production Readiness (agentfront/frontmcp, 146 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vercel Eve?

magnus919 (a GitHub user) maintains it in magnus919/agent-skills, which has 115 GitHub stars. The repository holds 131 skills in this directory. The repository was last updated on October 10, 2026.

Source: magnus919/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.