codex

Execute Codex CLI for code generation, analysis, web search and web fetch. Two capabilities - (1) Code Generation with deep reasoning, (2) Web Search & Fetch for online research.

⭐4stars🔀0forks📁View on GitHub🕐Updated Jan 1, 2026⬇️1downloads

When & Why to Use This Skill

The Codex CLI skill empowers Claude with advanced code generation, deep architectural analysis, and real-time web research capabilities. By leveraging high-reasoning models and integrated web fetching, it enables developers to perform complex refactoring, security audits, and live documentation lookups within a unified workflow, significantly accelerating the software development lifecycle.

Use Cases

  • Complex Codebase Refactoring: Utilize deep reasoning models to perform large-scale code restructuring and performance optimization across multiple files.
  • Automated Security & Logic Analysis: Scan entire project directories to identify potential security vulnerabilities, logic flaws, or architectural inconsistencies.
  • Real-Time Technical Research: Search for and fetch the latest API documentation, framework updates, or technology comparisons (e.g., Vite vs. Webpack) directly from the web.
  • GitHub Repository Summarization: Fetch content from specific GitHub repositories or technical blogs to generate concise summaries and implementation guides.
  • Multi-Turn Development Sessions: Resume previous coding tasks with session persistence to handle iterative development and follow-up refinements.
namecodex
descriptionExecute Codex CLI for code generation, analysis, web search and web fetch. Two capabilities - (1) Code Generation with deep reasoning, (2) Web Search & Fetch for online research.

Codex CLI Integration

Two specialized capabilities for different use cases.

Capability 1: Code Generation

Deep code analysis and generation with maximum reasoning power.

When to Use

  • Complex code analysis requiring deep understanding
  • Large-scale refactoring across multiple files
  • Automated code generation with safety controls
  • Tasks requiring specialized reasoning models

Default Configuration

  • Model: gpt-5.2-codex
  • Reasoning: xhigh (maximum thinking depth)

Command Pattern

codex e -m gpt-5.2-codex -c model_reasoning_effort=xhigh \
  --dangerously-bypass-approvals-and-sandbox \
  --skip-git-repo-check \
  -C <workdir> \
  "<task>"

Parameters

  • <task> (required): Task description, supports @file references
  • -m <model>: Override model (e.g., gpt-5.1-codex, gpt-5)
  • -c model_reasoning_effort=<level>: Override reasoning (low/medium/high/xhigh)
  • -C <workdir>: Working directory (default: current)

Examples

Basic code analysis:

codex e -m gpt-5.2-codex -c model_reasoning_effort=xhigh \
  --dangerously-bypass-approvals-and-sandbox \
  --skip-git-repo-check \
  "explain @src/main.ts"

Refactoring with custom model:

codex e -m gpt-5.1-codex -c model_reasoning_effort=high \
  --dangerously-bypass-approvals-and-sandbox \
  --skip-git-repo-check \
  "refactor @src/utils for performance"

Multi-file analysis:

codex e -m gpt-5.2-codex -c model_reasoning_effort=xhigh \
  --dangerously-bypass-approvals-and-sandbox \
  --skip-git-repo-check \
  -C /path/to/project \
  "analyze @. and find security issues"

Capability 2: Web Search & Fetch

Online research with web search and page content fetching.

When to Use

  • Online research and documentation lookup
  • Fetch and summarize specific web pages (GitHub repos, docs, articles)
  • Current information retrieval
  • API documentation search
  • Technology comparison and recommendations

Default Configuration

  • Model: gpt-5.1-codex
  • Reasoning: high
  • Web search: enabled

Command Pattern

codex e -m gpt-5.1-codex -c model_reasoning_effort=high \
  --enable web_search_request \
  --dangerously-bypass-approvals-and-sandbox \
  --skip-git-repo-check \
  "<task>"

Parameters

  • <task> (required): Search query or research task
  • -m <model>: Override model
  • -c model_reasoning_effort=<level>: Override reasoning (low/medium/high/xhigh)
  • --enable web_search_request: Enable web search (required for this capability)

Alternative: Config File

Add to ~/.codex/config.toml:

[features]
web_search_request = true

Examples

Fetch GitHub repo:

codex e -m gpt-5.1-codex -c model_reasoning_effort=high \
  --enable web_search_request \
  --dangerously-bypass-approvals-and-sandbox \
  --skip-git-repo-check \
  "Fetch and summarize https://github.com/user/repo"

Documentation search:

codex e -m gpt-5.1-codex -c model_reasoning_effort=high \
  --enable web_search_request \
  --dangerously-bypass-approvals-and-sandbox \
  --skip-git-repo-check \
  "find the latest React 19 hooks documentation"

Technology research:

codex e -m gpt-5.1-codex -c model_reasoning_effort=high \
  --enable web_search_request \
  --dangerously-bypass-approvals-and-sandbox \
  --skip-git-repo-check \
  "compare Vite vs Webpack for React projects in 2024"

Session Resume

Both capabilities support session resumption for multi-turn conversations.

Resume Command

codex e resume <session_id> "<follow-up task>"

Example

# First session (code generation)
codex e -m gpt-5.2-codex -c model_reasoning_effort=xhigh \
  --dangerously-bypass-approvals-and-sandbox \
  --skip-git-repo-check \
  "add comments to @utils.js"
# Output includes: thread_id in JSON output

# Continue the conversation
codex e resume <session_id> "now add type hints"

Notes

  • Requires Codex CLI installed and authenticated
  • @file syntax references files relative to working directory
  • @. references entire working directory
  • JSON output available with --json flag for programmatic use
  • All commands use --dangerously-bypass-approvals-and-sandbox for automation
  • Use --skip-git-repo-check to work in any directory