# Codex

> >

- **Type:** Skill
- **Install:** `agentstack add skill-dropfan-claude-code-plugins-codex`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [DropFan](https://agentstack.voostack.com/s/dropfan)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [DropFan](https://github.com/DropFan)
- **Source:** https://github.com/DropFan/claude-code-plugins/tree/master/plugins/codex-bridge/skills/codex

## Install

```sh
agentstack add skill-dropfan-claude-code-plugins-codex
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Codex Bridge

Route user requests to the appropriate Codex command. Commands handle context collection, prompt composition, and result analysis autonomously.

## Safety

- Default sandbox: `read-only`. Only use `workspace-write` on explicit user request.
- Forbidden flags: `--dangerously-bypass-approvals-and-sandbox` (and its alias `--yolo`), `--full-auto`, `--sandbox danger-full-access`
- Never pass secrets (API keys, tokens, passwords) in Codex prompts.

## Intent Classification & Routing

Classify the user's request and invoke the matching command. When the intent is ambiguous (e.g., "codex check this"), look at conversation context — if the user was just editing code and has uncommitted changes, lean toward review; otherwise default to general task.

### Review Intent → `/codex-bridge:codex-review`

Trigger when the request is about reviewing code changes, diffs, commits, or PRs.

Keywords: review, 审查, check changes, 看看改动, code review, PR review, diff review, check my code, 看看代码

Examples:
- "让 codex review 我的改动" → `/codex-bridge:codex-review`
- "codex 审查一下这个 PR" → `/codex-bridge:codex-review`
- "ask codex to review changes against main" → `/codex-bridge:codex-review main`
- "codex check my latest commit" → `/codex-bridge:codex-review HEAD`

Pass any branch name, commit SHA, or review instructions as arguments.

### General Task → `/codex-bridge:codex`

Trigger for all other requests: analysis, verification, second opinion, document review, task delegation.

Keywords: analyze, verify, explain, compare, delegate, check, 分析, 验证, 看看, 帮忙看

Examples:
- "让 codex 分析这个函数的错误处理" → `/codex-bridge:codex "分析...的错误处理"`
- "ask codex about the auth implementation" → `/codex-bridge:codex "analyze the auth implementation"`
- "codex 帮我看看这个插件的安全性" → `/codex-bridge:codex "review the security of this plugin"`

Pass the user's full request as the argument. The command will resolve context and compose the prompt.

### Ambiguous Cases

When the user's intent could match either command:
- If the user mentions "changes", "diff", "commit", or "PR" → review
- If the user mentions a specific file or function to analyze → general task
- If still unclear, ask the user: "Would you like Codex to review your recent changes, or analyze something specific?"

## Additional Resources

- **`references/usage-patterns.md`** — Detailed prompt templates for each usage pattern
- **`scripts/codex-exec.sh`** — Standalone wrapper for direct terminal use outside of Claude Code (commands invoke Codex CLI directly)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [DropFan](https://github.com/DropFan)
- **Source:** [DropFan/claude-code-plugins](https://github.com/DropFan/claude-code-plugins)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-dropfan-claude-code-plugins-codex
- Seller: https://agentstack.voostack.com/s/dropfan
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.