Agent skill

codex

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Resolves the latest flagship model from the model registry.

View SKILL.md on GitHub Repository
Stars 1
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/iamladi/cautious-computing-machine--sdlc-plugin/tree/main/skills/codex

SKILL.md

Codex Skill

Priorities

Correctness > Security > Efficiency

Model Registry

Load current models before executing — this overrides any model names in the tables below:

  • Glob(pattern: "**/sdlc/**/config/model-registry.md", path: "~/.claude/plugins") → Read result
  • Use codex-flagship as the default model. Offer user codex-fast for cost-sensitive tasks.
  • If registry load fails, fall back to the tables below.

Goal

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

Constraints

  • Default model: flagship from model registry (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 (fallback — prefer registry)

These model names may be outdated. Always prefer model-registry.md values when available.

Model Best for Context window Key features
gpt-5.3-codex Software engineering, code review, agentic coding 400K input / 128K output 25% faster, best agentic coding, $1.75/$14.00
gpt-5.3-codex-spark Research preview: ultra-fast inference via Cerebras 400K input / 128K output 1000+ tokens/s, experimental
gpt-5.2-codex Code review, security analysis 400K input / 128K output 79% SWE-bench Pro
gpt-5.1-codex Software engineering, agentic coding workflows 400K input / 128K output 76.3% SWE-bench, $1.25/$10.00
gpt-5.1-codex-mini Cost-efficient coding (4x more usage allowance) 400K input / 128K output Near SOTA performance, $0.25/$2.00

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

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

iamladi/cautious-computing-machine--sdlc-plugin

tdd

TDD enforcement during implementation. Reads `tdd:` setting from CLAUDE.md. Modes - strict (human approval for escape), soft (warnings), off (disabled). Auto-invoked by /implement.

1 0
Explore
iamladi/cautious-computing-machine--sdlc-plugin

judgment-eval

Evaluates agent judgment quality through scenario-based testing in-conversation. Use when the user wants to test, validate, or stress-test an agent, skill, or command definition — e.g. "test this agent", "evaluate this skill", "does this prompt handle edge cases", "check this agent's judgment", or after writing or modifying any agent/skill/command .md file.

1 0
Explore
iamladi/cautious-computing-machine--sdlc-plugin

update-models

Re-resolve the model registry by querying OpenAI Codex cache, Google AI API, and Oracle CLI. Use when models feel stale or after a major model release.

1 0
Explore
iamladi/cautious-computing-machine--sdlc-plugin

gemini

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Resolves the latest flagship model from the model registry.

1 0
Explore
iamladi/cautious-computing-machine--sdlc-plugin

agent-change-walkthrough

Generates a narrative walkthrough of AI-authored code changes. Use after implementation to explain what changed, why, and how it behaves.

1 0
Explore
iamladi/cautious-computing-machine--sdlc-plugin

finish-branch

1 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results