Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →k9i-0/codex-guide
Codex の使い方、CLI/app/IDE、rules・hooks・AGENTS.md・skills・subagents・config などを案内する。Codex や OpenAI 製品の仕様を答える前に必ず公式ドキュメントを確認し、rules/approval は `codex execpolicy check` で実検証すること。
Passed 11 of 17 test cases with the skill, and 6 of 17 without it.
and 4 more in the full report
7 fixed7 passed either way7 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
What exact CLI command and options should I run to dry-run test a newly drafted rules file against the command `rm -rf /tmp/build` before applying it?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies the command `codex execpolicy check`. | Missed | Passed |
The instructions your model reads when the skill loads.
Codex の使い方や仕様を案内するときのガイド。
rules, execpolicy, approvals, hooks, AGENTS.md, skills, subagents, MCP, config を説明するときcodex execpolicy check で実際の判定を確認する。allow / prompt / forbidden を確かめる。用途ごとに references/official-sources.md の該当ページを開く。
openai/codex変更提案前に、少なくとも以下を実行する。
codex execpolicy check --pretty --rules <rules-file> -- <command...>
最低 2 パターン確認すること。
test cases passed, vs 6 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.