Back to Skills
Skill

codex

From sdlc
1
Install
1
Install the plugin
$
npx claudepluginhub iamladi/cautious-computing-machine --plugin sdlc

Want just this skill?

Add to a custom plugin, then install with one command.

Description

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.3-Codex by default for state-of-the-art software engineering.

Tool Access

This skill uses the workspace's default tool permissions.

Supporting Assets
View in Repository
references/codex-cli-reference.md
Skill Content

Codex Skill

Priorities

Correctness > Security > Efficiency

Goal

Execute OpenAI Codex CLI for automated code analysis, refactoring, and editing tasks. Default to gpt-5.3-codex model with user-specified reasoning effort. Suppress stderr thinking tokens by default unless debugging is needed.

Constraints

  • Default model: gpt-5.3-codex (ask user for reasoning effort: high, medium, or low)
  • Sandbox mode: --sandbox read-only (default), workspace-write (for edits), danger-full-access (network/broad access)
  • Always use --skip-git-repo-check flag
  • Suppress stderr by default: append 2>/dev/null to all codex exec commands
  • Resume sessions: echo "prompt" | codex exec --skip-git-repo-check resume --last 2>/dev/null (no config flags between exec and resume unless user specifies)
  • Ask permission before using high-impact flags (--full-auto, --sandbox danger-full-access)
  • Stop and report on non-zero exit codes
  • Inform user after completion: "You can resume this Codex session at any time by saying 'codex resume'"

Model Options

ModelBest forContext windowKey features
gpt-5.3-codex ⭐⭐Flagship model: Software engineering, code review, agentic coding400K input / 128K output25% faster, best agentic coding, $1.75/$14.00
gpt-5.3-codex-sparkResearch preview: ultra-fast inference via Cerebras400K input / 128K output1000+ tokens/s, experimental
gpt-5.2-codexCode review, security analysis400K input / 128K output79% SWE-bench Pro
gpt-5.1-codex ⭐Software engineering, agentic coding workflows400K input / 128K output76.3% SWE-bench, $1.25/$10.00
gpt-5.1-codex-miniCost-efficient coding (4x more usage allowance)400K input / 128K outputNear SOTA performance, $0.25/$2.00
gpt-5.1-thinkingUltra-complex reasoning, deep problem analysis400K input / 128K outputAdaptive thinking depth, runs 2x slower on hardest tasks

References

Load CLI reference and code review patterns:

  • Glob(pattern: "**/sdlc/**/skills/codex/references/codex-cli-reference.md", path: "~/.claude/plugins") → Read result

Arguments

$ARGUMENTS

Stats
Stars1
Forks0
Last CommitFeb 12, 2026
Actions

Similar Skills