dot_claude/skills/codex/SKILL.md
Use ONLY when explicitly asked to invoke or run the Codex CLI tool for agentic review. Do NOT trigger when "codex" appears in conversation as a model name, topic, or reference.
npx skillsauth add nijaru/dotfiles codexInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use when you want a different model to walk the repo autonomously — useful for pre-release review or validating invariants you can't easily enumerate upfront.
# Review against base branch
codex review --base main -o /tmp/codex-review.txt
# Freeform analysis
echo "Find all places where X invariant could be violated" | codex exec --full-auto -o /tmp/codex-reply.txt
Always use -o <file> — findings are lost without it.
codex --dangerously-bypass-approvals-and-sandbox -C /absolute/path/to/repo "prompt"
development
Use after completing a bug fix, feature, refactor, or tk task when the first implementation taught enough context to replace it with a simpler, cleaner, or more coherent version before finalizing.
development
Use when writing, migrating, or reviewing Zig code across recent stable versions (0.14-0.16), especially to correct stale syntax or stdlib, build.zig, allocator, formatting, or runtime API knowledge.
documentation
Use when reviewing or revising text (prose, docs, commits) to remove AI patterns and improve voice/clarity.
content-media
Use when fetching X/Twitter post content by URL, or searching for recent X posts.