Agent skill
claude-codex
Use the local Codex CLI from Claude Code with the user's existing Codex login or API key. Use for Codex reviews, second-opinion analysis, implementation delegation, or non-interactive Codex runs in the current workspace.
Install this agent skill to your Project
npx add-skill https://github.com/sonichi/sutando/tree/main/skills/claude-codex
SKILL.md
Claude Codex
Delegate work from Claude Code to the local codex CLI. This skill assumes Codex is already authenticated on this machine. It does not mint, extract, or transfer credentials.
Usage: /claude-codex [prompt]
ARGUMENTS: $ARGUMENTS
When to Use
- "Ask Codex to review this change"
- "Use my Codex subscription from Claude Code"
- Need a second model to inspect a bug, review a diff, or propose an implementation
- Need a Codex result saved or streamed from the current repo
Guardrails
- Prefer
codex review --uncommittedfor code review. - Prefer
codex execfor analysis, planning, or implementation prompts. - Keep Codex pointed at the same repo with
-C "$PWD"unless the user asked for another directory. - Default to
workspace-writesandbox or stricter. Do not use bypass flags unless the user explicitly asks.
Quick Checks
codex login status
bash "$SKILL_DIR/scripts/codex-run.sh" --check
Common Commands
# General delegation
bash "$SKILL_DIR/scripts/codex-run.sh" -- "Inspect src/task-bridge.ts for race conditions"
# Safer review of current uncommitted changes
bash "$SKILL_DIR/scripts/codex-run.sh" --review --uncommitted -- "Prioritize bugs and missing tests"
# Review against a base branch
bash "$SKILL_DIR/scripts/codex-run.sh" --review --base main -- "Focus on regressions and security"
# Save the last Codex message to a file
bash "$SKILL_DIR/scripts/codex-run.sh" --output-last-message results/codex-review.txt -- "Review the current workspace"
If Invoked As A Slash Command
- If ARGUMENTS is empty, explain the available modes and suggest
--review --uncommittedfor diffs or a plain prompt for general delegation. - If ARGUMENTS is present, run:
bash "$SKILL_DIR/scripts/codex-run.sh" -- "$ARGUMENTS"
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
x-twitter
Post tweets, search, read mentions, and check engagement on X (Twitter) via API v2.
schedule-crons
phone-conversation
Make conversational phone calls and join Zoom meetings via Twilio + Gemini. Multi-turn AI conversations on the phone on behalf of the user.
screen-record
quota-tracker
Track Claude Code quota usage via Anthropic API rate limit headers. Shows 5h and 7d utilization, reset times, and quota status. Works with both subscription and API key auth.
proactive-loop
Start Sutando's autonomous proactive loop. Monitors tasks, runs health checks, and builds missing capabilities on a recurring schedule.
Didn't find tool you were looking for?