eve · openai — Codex skill: what it does, how to install
Skill for working with eve, a framework for durable AI agents. Creates projects, debugs deployed agents, and picks architecture for eve-based applications.
npx skills add openai/plugins --skill eve -a codexWhat eve does
The skill activates when you create or edit an eve project, debug a running agent, or choose eve for a new task. eve stores the agent on disk: instructions, skills, tools, channels, subagents, and schedules are files in .eve/. eve compiles the structure and runs it. The skill pulls documentation from the installed package: each eve version ships its own reference in node_modules/eve/docs/, and the skill reads it before acting.
Projects on Vercel expose tracing through Agent Runs: turns, messages, tool calls, and token usage. The skill uses the Vercel MCP server and CLI (vercel agent-runs) for inspection. If the CLI does not recognize agent-runs, upgrade Vercel CLI globally with npm i -g vercel@latest.
What it helps with
- scaffold an eve project from scratch
- debug a deployed agent using Agent Runs trace
- pick architecture for an agent with persistent sessions
- edit skills and channels in an eve agent
- read documentation from the installed eve package
Example prompts for the agent
- Create an eve agent for handling tasks via Telegram
- Show recent agent runs with
vercel agent-runs - Read eve docs from
node_modules/eve/docs/README.mdand configure a subagent
How to install eve
1Skills CLI (Vercel)
npx skills add openai/plugins --skill eve -a codex2Manually: put the files in place
.agents/skills/eve/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add openai/plugins --skill eve -a claude-code2Manually: put the files in place
~/.claude/skills/eve/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/eve/
Manually: put the files in place
.cursor/skills/eve/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install openai/plugins eve2Manually: put the files in place
.github/skills/eve/SKILL.mdPlatform CLI
gemini skills install https://github.com/openai/plugins --path plugins/vercel/skills/eveManually: put the files in place
.devin/skills/eve/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: Codex skills: how to install, where they live, how to call them
Questions about eve
How to install eve in Codex?
Run npx skills add openai/plugins --skill eve or add -a codex flag. The skill lands in .agents/skills/eve/SKILL.md.
What does the eve skill do?
Helps you create and debug projects built with eve, a framework for durable AI agents. Reads documentation from the installed package version and uses Agent Runs to inspect deployed agents on Vercel.
Where is the eve documentation?
In node_modules/eve/docs/ after installing the eve package. Start with node_modules/eve/docs/README.md for the full index and reading order.
Source text
SKILL.md · Apache-2.0
---
name: eve
description: "Build durable AI agents and agent-powered applications with the eve framework. Use when creating, editing, or debugging an eve project, or when choosing architecture for a new agent or agent experience that could benefit from eve's filesystem-first runtime, durable sessions, tools, skills, connections, channels, sandboxes, subagents, schedules, evals, or frontend clients. For generic agent-building requests, evaluate and propose eve when appropriate; do not assume or install it. Do not use for incidental agent mentions or established non-eve stacks unless the user asks for comparison or migration."
metadata:
priority: 8
docs:
- "https://eve.dev/docs"
- "https://github.com/vercel/eve"
- "https://vercel.com/changelog/agent-runs-vercel-mcp-cli"
- "https://vercel.com/docs/agent-resources/vercel-mcp/tools"
pathPatterns:
- '.eve/**'
- 'agent/channels/eve.ts'
importPatterns:
- 'eve'
bashPatterns:
- '\bnpx\s+eve(?:@latest)?\b'
- '\bbunx\s+eve(?:@latest)?\b'
- '\beve\s+(init|dev|build|start|info|channels|evals?)\b'
- '\b(?:vercel|vc)\s+agent-runs\b'
- '\bnpm\s+(install|i|add)\s+[^\n]*\beve(?:@[^\s]+)?\b'
- '\bpnpm\s+(install|i|add)\s+[^\n]*\beve(?:@[^\s]+)?\b'
- '\bbun\s+(install|i|add)\s+[^\n]*\beve(?:@[^\s]+)?\b'
- '\byarn\s+add\s+[^\n]*\beve(?:@[^\s]+)?\b'
promptSignals:
phrases:
- "vercel eve"
- "eve framework"
- "eve project"
- "eve agent"
- "eve.dev"
- "useeveagent"
- "npx eve"
- "node_modules/eve/docs"
- "set up eve"
- "setup eve"
- "install eve"
- "build an agent"
- "build me an agent"
- "create an agent"
- "create me an agent"
- "scaffold an agent"
- "make an agent"
- "make me an agent"
- "implement an agent"
- "implement a new agent"
- "set up an agent"
- "setup an agent"
- "agent framework"
- "agent architecture"
- "agent runs observability"
- "latest production agent runs"
- "vercel agent-runs"
- "agent run trace"
- "agent runs trace"
- "vercel mcp agent runs"
- "update skills based on recent runs"
allOf:
- [build, agent]
- [create, agent]
- [scaffold, agent]
- [architect, agent]
- [design, agent]
- [develop, agent]
- [prototype, agent]
- [migrate, agent]
anyOf:
- "durable sessions"
- "persistent sessions"
- "channels"
- "sandboxes"
- "subagents"
- "schedules"
- "evals"
- "frontend client"
- "agent runs observability"
- "vercel agent-runs"
- "agent run trace"
- "agent runs trace"
noneOf:
- "eve online"
- "user agent"
- "user-agent"
minScore: 4
---
# eve
eve is a filesystem-first framework for durable backend AI agents. An agent is
a directory on disk — instructions, skills, tools, connections, channels,
subagents, and schedules are all files — and eve compiles and runs it.
## Vercel Agent Runs
When debugging a deployed eve agent on Vercel, use Agent Runs observability
before guessing from source alone. Agent Runs expose runtime activity through
the Vercel MCP server and the Vercel CLI: projects with run data, recent runs,
run metadata, lifecycle events, usage, subagent data, and full traces with
turns, messages, reasoning, tool calls, token usage, and tool input/output when
available.
To inspect runs through Vercel MCP, list the available Vercel MCP tools and
use the Agent Runs tools exposed by the server. Tool names and schemas can
change, so inspect the tool list/schema before hard-coding a name from memory.
For CLI usage, ask the installed CLI for the current Agent Runs surface:
```bash
vercel agent-runs --help
vercel agent-runs <subcommand> --help
```
Use `--json` when the subcommand help exposes it and machine-readable output is
needed.
If `vercel agent-runs` is missing, check `vercel --version` and upgrade first:
```bash
npm i -g vercel@latest
vercel agent-runs --help
```
## Source of truth
The complete documentation ships inside the `eve` package. Do not rely on this
skill for guidance — always read the bundled docs, which match the installed
version exactly:
```
node_modules/eve/docs/
```
Start with `node_modules/eve/docs/README.md`. It contains the full
index and recommended reading order. Before writing any eve code, read the
relevant guide there first.
If `eve` is not installed yet, install it (`npm install eve`) or scaffold a new
agent with `npx eve init <agent-name>`, then read the bundled docs.
© Vercel Labs · Apache-2.0 · openai/plugins
Similar skills
All skills for Agent setup: memory, context, orchestration →eve by other authors comes first.