vercel · Vercel
Vercel CLI Agent 使用指南
无需依赖控制台即可创建、检查和提升 Vercel 部署。
官方工具操作风险: R2–R3docs-verified
为 Agent 安装
选择与运行环境匹配的官方安装方式。在团队或 CI 环境中固定版本，并先运行版本检查。
用于稳定自动化的结构化输出
优先使用机器可读格式，并把 stdout 作为结果、stderr 作为诊断信息分别处理。
R0–R3 命令风险指南
风险按单条命令判断。R0 是本地或远程只读，R1 是可逆的本地写入，R2 会改变远程状态，R3 可能造成不可逆或生产级影响。
只读不等于可公开
R0 只表示命令不更改本地或远程状态。只读命令仍可能返回令牌、身份信息、配置或生产数据；只展示完成任务所需的最少内容，不得写入日志、Prompt 或提交内容。
Agent Readiness 评分依据
适配度描述 Agent 操作工具的稳定程度，不代表所有命令都安全，也不替代独立执行测试。
文档证据对应的 Agent Readiness 为 84/100；尚未记录本地执行测试。
生成 Skill 或 Agent 策略
选择目标 Agent 和安全模式，生成包含安装、允许命令、确认边界与证据说明的可复制产物。
生成结果预览
SKILL.md
---
name: vercel-cli-agent-workflow
description: Use Vercel CLI for preview deployments, production deploys, logs with explicit command risk and evidence boundaries.
---
# Vercel CLI agent workflow
Use this skill when the task needs preview deployments, production deploys, logs, environment variables.
## Evidence boundary
- Registry confidence: `docs-verified`
- Documentation checked: `2026-07-10`
- Locally tested version: `not tested`
- Do not describe this CLI as locally verified until its commands have actually been executed in an isolated environment.
## Executed smoke checks
- No local execution record is available.
## Installation
- npm (macos, linux, windows): `npm install --global vercel`
## Authentication
- Methods: browser login, access token
- Secret environment variables: `VERCEL_TOKEN`, `VERCEL_ORG_ID`, `VERCEL_PROJECT_ID`
- Minimum permissions: Use a token scoped to the target team and project; keep production promotion separate.
- Credential storage: For headless runs, inject VERCEL_TOKEN, VERCEL_ORG_ID, VERCEL_PROJECT_ID from the CI or platform secret manager at process start. For local interactive use, prefer the CLI or operating-system credential store when the official client supports one. Never save values in repository files.
- Never print, persist, or commit credential values.
## Allowed commands (read-only)
- `vercel inspect https://example.vercel.app --json` — R0: Reads deployment status and metadata.
## Commands requiring explicit approval (read-only)
- None recorded.
## Forbidden commands (read-only)
- R2 `vercel --yes` — Uploads code and creates a remote preview deployment.
- R3 `vercel --prod --yes` — Changes production traffic and must be explicitly approved.
## Execution rules
1. Mode boundary: R0 exact commands may be used; R1, R2, and R3 commands are forbidden.
2. Confirm the selected account, project, context, database, namespace, or environment before any command.
3. Prefer structured output using `--json`, `--yes`.
4. Capture the exact command, exit code, stdout, and stderr separately.
5. A generated prefix policy must prompt unless that exact prefix is explicitly marked suffix-safe; do not infer safety from the executable name.
6. Never broaden credentials or disable safety controls to make a command succeed.
## Official sources
- [Vercel CLI documentation](https://vercel.com/docs/cli)
- [Vercel CLI documentation source repository](https://github.com/vercel/vercel)
验证记录与官方证据
CLI Finder 分开记录文档检查和真实执行。未执行过的安装、帮助、退出码与输出不能标为 Verified。