# 14.9 How today's tools realize it (/building-ai-workers/structuring-programs/both-ai-vendors) --- type: Document title: "14.9 How today's tools realize it" description: "Where Claude Code, Codex and OpenCode differ when they install a package, reach a server on your own computer, keep it running and review a change, as their own pages said on October 30, 2026." status: stable order: 314.09 ksor: owner: team:panaversity audience: [ public ] approval: by: process:panaversity at: 2026-11-09T15:49:29Z chapter: "14" part: III expert_status: builder-only concepts: [ "14.9" ] last_verified: 2026-10-30 sources: - id: anthropic-permission-modes title: "Permission modes (Anthropic, accessed 2026-10-30)" resource: https://code.claude.com/docs/en/permission-modes - id: anthropic-sandboxing title: "Sandboxing (Anthropic, accessed 2026-10-30)" resource: https://code.claude.com/docs/en/sandboxing - id: anthropic-interactive-mode title: "Interactive mode (Anthropic, accessed 2026-10-30)" resource: https://code.claude.com/docs/en/interactive-mode - id: anthropic-code-review-local title: "Review locally with /code-review (Anthropic, accessed 2026-10-30)" resource: https://code.claude.com/docs/en/code-review-local - id: anthropic-team-enterprise title: "Use Claude Code with your Team or Enterprise plan (Anthropic, verified 2026-11-01)" resource: https://support.claude.com/en/articles/11845131-use-claude-code-with-your-team-or-enterprise-plan - id: anthropic-pro-max title: "Use Claude Code with your Pro, Max, or Ultra plan (Anthropic, accessed 2026-10-31)" resource: https://support.claude.com/en/articles/11145838-use-claude-code-with-your-pro-max-or-ultra-plan - id: openai-agent-approvals title: "Agent approvals and security (OpenAI, accessed 2026-10-30)" resource: https://learn.chatgpt.com/docs/agent-approvals-security - id: openai-developer-commands title: "Commands (OpenAI, accessed 2026-10-30)" resource: https://learn.chatgpt.com/docs/developer-commands?surface=cli - id: openai-code-review title: "Code review (OpenAI, accessed 2026-10-30)" resource: https://learn.chatgpt.com/docs/code-review - id: openai-codex-pricing title: "Codex pricing (OpenAI, accessed 2026-10-30)" resource: https://learn.chatgpt.com/docs/pricing - id: opencode-permissions title: "Permissions (OpenCode, accessed 2026-10-30)" resource: https://opencode.ai/v2/docs/permissions/ - id: opencode-tools title: "Tools (OpenCode, accessed 2026-10-30)" resource: https://opencode.ai/v2/docs/tools/ - id: opencode-security title: "Security policy and advisories (OpenCode, accessed 2026-10-30)" resource: https://github.com/anomalyco/opencode/security - id: opencode-changelog title: "Changelog (OpenCode, accessed 2026-10-30)" resource: https://opencode.ai/changelog - id: opencode-releases title: "Releases (OpenCode, accessed 2026-10-31)" resource: https://github.com/anomalyco/opencode/releases generated: at: 2026-11-09T15:49:29Z by: process:panaversity trust_tier: unverified build_id: sha256:46fd53c5d7ab1c14f6347908d45c9fdaecda4d914439923ee878bdcecd57803e dirty: true ksor_version: 0.0.60 --- **In everyday life.** Three office buildings all take deliveries. In the first, the front desk calls you before any parcel comes up. In the second, the doors stay locked, and you let each driver in yourself. In the third, drivers walk straight in unless you post your own rule at the door. In every building, you read the label before you sign for the parcel. **What you will learn.** Where Claude Code, Codex and OpenCode differ when they install a package, reach a server on your own computer, keep it running and review a change, as of October 30, 2026. **Why it matters.** Claude Code is the front desk: it asks before each install. Codex is the locked door: its sandbox keeps the network off until you approve. OpenCode is the open door, until you set its rules. The parcel is the package. Your part does not change: you decide, you predict, the agent runs it, and you read what really happened. **How to use this page.** This page holds only what differs by tool. Pick your tool once, and every strip on this page follows. ## How does each agent ask before it installs a package? In these tabs, a sandbox is not the throwaway machine of [12.3](../agentic-coding/permissions-and-plan.md). It is a set of limits on your own computer. ### Claude Code An install, such as `npm ci`, `npm install zod` or `uv add pydantic`, is a shell command, so Claude Code asks before each one in *Manual* and *Accept edits* modes.[^anthropic-permission-modes] Read the package name in the prompt before you approve. Use *Manual* for this page. ### Codex In the *workspace-write* sandbox, network access is off by default, and Codex asks for approval before a command that needs the network, such as `npm install`.[^openai-agent-approvals] So expect it to ask before `npm ci` and `uv sync`, which download packages. Use *Ask for approval* for this chapter's Try it steps. ### OpenCode OpenCode runs `npm` and `uv` with your own rights.[^opencode-tools] Before your first message in a folder, set edits and the `shell` action to ask, as in [Lab 12](../agentic-coding/lab.md), so each command and each install waits for you.[^opencode-permissions] OpenCode does not sandbox the agent.[^opencode-security] ## How does each agent reach a server on your own computer? Whichever agent you use, a server it starts is stopped when the task ends. ### Claude Code A local session has no network limit by default. With the sandbox on, a local test server needs an exception.[^anthropic-sandboxing] Claude Code can run a long-running command, such as a development server, in the background while it keeps working. `/tasks` lists background tasks.[^anthropic-interactive-mode] ### Codex OpenAI's security page says that when its network proxy is on, local and private addresses such as `localhost` are blocked unless you allow them. The proxy is off by default.[^openai-agent-approvals] So check here whether your Codex session can reach the sample API, before the lab needs it, and allow it in your settings if it cannot. Codex can run commands in background terminals. `/ps` lists them with their recent output, and `/stop` stops them.[^openai-developer-commands] ### OpenCode A shell command has your full file, process and network authority, so it can reach `localhost` and the internet alike.[^opencode-tools] The shell tool can start a command in the background.[^opencode-tools] Before the task ends, check the process list and stop what is still running. The key here is made up. With a real key, remember that OpenCode can read any file your account can. ## How does each agent review a change? ### Claude Code Run `/code-review` before the commit.[^anthropic-code-review-local] ### Codex `/review` reports findings on your uncommitted changes or your branch, without changing files.[^openai-code-review] ### OpenCode OpenCode's version 2 documentation describes no review command. Read its review panel or `git diff` instead.[^opencode-changelog] ## What it costs ### Claude Code Claude Code comes with the Pro, Max and Ultra plans,[^anthropic-pro-max] and with Team and Enterprise seats that include it, as of November 1, 2026.[^anthropic-team-enterprise] ### Codex Codex is on every ChatGPT plan, including Free.[^openai-codex-pricing] ### OpenCode OpenCode is free under the MIT license, at version 2.2.5 on October 30, 2026.[^opencode-releases] You pay for the model you connect. [^anthropic-permission-modes]: Permission modes, Anthropic. [^anthropic-sandboxing]: Sandboxing, Anthropic. [^anthropic-interactive-mode]: Interactive mode, Anthropic. [^anthropic-code-review-local]: Review locally with /code-review, Anthropic. [^anthropic-pro-max]: Use Claude Code with your Pro, Max, or Ultra plan, Anthropic. [^anthropic-team-enterprise]: Use Claude Code with your Team or Enterprise plan, Anthropic. [^openai-agent-approvals]: Agent approvals and security, OpenAI. [^openai-developer-commands]: Commands, OpenAI. [^openai-code-review]: Code review, OpenAI. [^openai-codex-pricing]: Codex pricing, OpenAI. [^opencode-tools]: Tools, OpenCode. [^opencode-permissions]: Permissions, OpenCode. [^opencode-security]: Security policy and advisories, OpenCode. [^opencode-changelog]: Changelog, OpenCode. [^opencode-releases]: Releases, OpenCode.