Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/codex-agent
作为项目经理操作 OpenAI Codex CLI 完全体。包含：知识库维护（自动跟踪 Codex 最新功能）、任务执行（提示词设计→执行→监控→质量检查→迭代→汇报）、配置管理（feature flags/模型/skills/MCP）。通过 tmux 操作交互式 TUI，通过 notify hooks + pane monitor 实现异步唤醒。NOT for: 简单单行编辑（用 edit）、读文件（用 read）、快速问答（直接回答）。
Passed 2 of 8 test cases with the skill, and 1 of 8 without it.
and 2 more in the full report
4 fixed2 passed either way15 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Where are task execution logs and schema validation records stored by the task runner script when running a package named 'auth-service'?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies .claude/state/logs/auth-service/ as the log directory path. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill enables Claude Code to collaborate with OpenAI's Codex CLI agent for second-opinion review, cross-verification, debugging analysis, and alternative implementation proposals.
Default posture: Codex reviews in read-only; the primary agent applies changes only when the user asked for fixes or approved them after reading the review.
Use this workflow when the user asks for Codex review, wants a second opinion, or needs cross-verification from a separate coding agent.
REPORT="$(mktemp -t codex-review.XXXXXX.md)"
codex exec -C <project_path> -s read-only -o "$REPORT" \
"Review the code in <file_or_directory>. Check for:
- Security vulnerabilities
- Performance issues
- Code quality and best practices
- Potential bugs and edge cases
- Naming and readability
Provide specific, actionable feedback with file paths and line numbers."
cat "$REPORT"
Keep the write and read in the same Bash call, or pass a concrete report path between calls; shell variables do not persist across tool calls.
When the user asked to apply fixes, handle each issue identified by Codex:
If the user only asked for a review or second opinion, report findings without editing files.
test cases passed, vs 1 / 8 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.