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. Uses GPT-5.2 by default for state-of-the-art software engineering.
86
83%
Does it follow best practices?
Impact
88%
4.00xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Evaluation results
84%
67%Automated Code Review Script
Correct command assembly
Default model gpt-5.2
0%
100%
skip-git-repo-check flag
0%
100%
stderr suppression
16%
100%
Read-only sandbox
0%
100%
Reasoning effort flag syntax
0%
100%
Version check included
87%
100%
Full-auto NOT used
0%
0%
Exit code handling
100%
100%
Resume hint present
0%
0%
Model reasoning effort level appropriate
0%
100%
Valid model name only
0%
100%
86%
55%Legacy Code Modernization Tool
Sandbox mode and write access
workspace-write sandbox
0%
100%
full-auto flag present
0%
100%
skip-git-repo-check flag
100%
100%
stderr suppression
0%
100%
Default model gpt-5.2
0%
100%
Reasoning effort configured
0%
100%
Permission request documented
30%
40%
Exit code handling
100%
75%
danger-full-access NOT used
100%
100%
Resume session note
0%
0%
96%
76%Multi-Session Security Audit Runbook
Session resume workflow
Pipe-based resume syntax
0%
100%
resume --last flag
100%
100%
skip-git-repo-check in resume
0%
100%
stderr suppression on resume
0%
100%
No config flags on resume
0%
100%
Flags between exec and resume
50%
100%
Session inherits settings note
0%
100%
Post-completion resume hint
37%
50%
Initial run uses correct model
0%
100%
Initial run stderr suppression
0%
100%
- Repository
- softaworks/agent-toolkit
- Commit
3027f20
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.