Skip to content
Back to skills

Update Cli Config

ASecurity

CLI 配置修改。查看或修改 Codex/兼容 CLI 的配置。

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 16, 2026
ai-agents

Works with

  • cursor
  • cli

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 16, 2026

npx -y skills add 0mlkrizzz655335v/claude-skills-zh --skill update-cli-config --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Update Cli Config?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Update Cli Config
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/0mlkrizzz655335v-update-cli-config/badge)](https://www.skillsdirectory.com/skills/0mlkrizzz655335v-update-cli-config)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: update-cli-config
description: "CLI 配置修改。查看或修改 Codex/兼容 CLI 的配置。"
metadata:
  surfaces:
    - cli
---


# CLI Configuration

Inspect and modify the configuration of the user's Codex or compatible agent CLI. Identify its executable/version, current configuration root, and applicable project overrides before selecting a file or schema. Use existing local configuration/help first and current official docs when necessary. For Codex-specific questions, use the installed `openai-docs` skill as appropriate.

For the runtime that supports `~/.cursor/cli-config.json` with `.cursor/cli.json` project overrides, read [CLI JSON settings](references/cli-json.md). Other runtimes may use a different path and format; do not create this file as a universal Codex default or copy its permission keys into another schema.

Make only the requested changes and keep a recoverable copy. Preserve unknown fields, unrelated overrides, authentication/cache state, and the user's formatting where possible. Avoid printing credentials while inspecting configuration.

Permission, approval, and sandbox changes must match the user's requested behavior and the current runtime's documented legal values. Do not guess a value from “non-allowlist,” a UI label, or an old example. Editing a file does not alter the permissions of the current agent session.

Validate the actual format and diff, then verify acceptance through the runtime's supported inspection/startup mechanism when possible. Explain any required restart, distinguishing a saved setting from a confirmed new-process or live behavior check.

Files in this skill

  • SKILL.md1.6 KB
  • references/cli-json.md4.4 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.