Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.
npx skills add https://github.com/majiayu000/spellbook --skill codex-agent
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 "$REPORT"
Keep the write and read in the same Bash call, or pass a concrete report path
between calls; shell variables do not persist across tool calls.
When the user asked to apply fixes, handle each issue identified by Codex:
If the user only asked for a review or second opinion, report findings without editing files.
codex exec -C <project_path> -s read-only \
"Verify the fixes applied to <files>. Confirm issues are resolved."
# Step 1: Get Codex review
REPORT="$(mktemp -t codex-review.XXXXXX.md)"
codex exec -C /project -s read-only -o "$REPORT" \
"Review src/auth/login.ts for security vulnerabilities and code quality issues. Provide specific line numbers and fixes."
# Step 2: Read the feedback
cat "$REPORT"
Then the primary agent reads the feedback, applies fixes with Edit tool, and optionally re-verifies.
# Get diff of recent changes
DIFF_REPORT="$(mktemp -t recent-changes.XXXXXX.diff)"
git diff HEAD~1 > "$DIFF_REPORT"
# Step 1: Have Codex review the diff
REPORT="$(mktemp -t codex-review.XXXXXX.md)"
codex exec -C /project -s read-only -o "$REPORT" \
"Review the changes saved at $DIFF_REPORT. Check for bugs, security issues, and improvements needed."
# Step 2: Read and apply fixes
cat "$REPORT"
# Step 1: Comprehensive review
REPORT="$(mktemp -t codex-review.XXXXXX.md)"
codex exec -C /project -s read-only -o "$REPORT" \
"Perform a comprehensive code review of src/. Focus on:
1. Security vulnerabilities (OWASP Top 10)
2. Error handling patterns
3. Performance bottlenecks
4. Code duplication
Prioritize issues by severity (critical/high/medium/low)."
# Step 2: Read prioritized feedback
cat "$REPORT"
When asking Codex for review, include:
Review <target_files_or_directory>.
Context:
- Project type: <TypeScript/Python/etc>
- Framework: <Express/React/etc>
- Focus areas: <security/performance/quality>
Check for:
1. Security vulnerabilities
2. Performance issues
3. Error handling
4. Code quality
5. Edge cases
Output format:
For each issue:
- File: <path>
- Line: <number>
- Severity: critical/high/medium/low
- Issue: <description>
- Fix: <specific code change>
After receiving Codex feedback, apply fixes systematically:
Codex CLI must be installed and authenticated:
# Install via npm
npm install -g @openai/codex
# Or via Homebrew (macOS)
brew install --cask codex
# Authenticate
codex login
codex exec [options] "<task_description>"
| Option | Description |
|--------|-------------|
| "<task>" | Task description (positional, must be quoted) |
| -C <dir> | Working directory (use absolute path) |
| -s read-only | Read-only sandbox (use for reviews) |
| -o <path> | Save output to file |
| --json | Output as JSON Lines |
When communicating with Codex, PRIORITIZE ACCURACY AND PRECISION:
codex exec -C /project -s read-only \
"Verify the implementation in src/feature/. Check correctness and edge cases."
REPORT="$(mktemp -t codex-alternative.XXXXXX.md)"
codex exec -C /project -s read-only -o "$REPORT" \
"Propose an alternative implementation for the caching in src/cache/manager.ts"
cat "$REPORT"
codex exec -C /project -s read-only \
"Debug: tests in tests/auth.test.ts failing with timeout. Analyze root cause."
For multi-turn reviews:
# Initial review
codex exec -C /project -s read-only "Review src/api/ for security issues"
# Note session ID from output
# Follow-up after fixes
codex exec resume <session_id> "I've applied the fixes. Please re-verify."
scripts/check-codex.sh checks whether the Codex CLI is installed and authenticated.scripts/codex-wrapper.sh is optional. Use it only when you need a small CLI wrapper; it executes Codex through shell arrays and must not use eval./tmp/codex-review.md; use mktemp or a project-specific private report path so concurrent projects cannot overwrite or read stale feedback.read-only unless the user explicitly asked Codex itself to edit.danger-full-access, --dangerously-bypass-approvals-and-sandbox, --dangerously-bypass-hook-trust, and --skip-git-repo-check as high-impact flags. Ask before using them.codex logout
codex login
codex --version
which codex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Replace with description of the skill and when Claude should use it.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Take majiayu000/spellbook-codex-agent from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npm, brew.
Without those the skill loads but fails at the first command.