Menu
Invokes Codex CLI for code analysis, refactoring, or automated editing. Use when the user asks to run codex exec, codex resume, or references OpenAI Codex.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | codex |
| description | Invokes Codex CLI for code analysis, refactoring, or automated editing. Use when the user asks to run codex exec, codex resume, or references OpenAI Codex. |
| license | MIT |
| context | fork |
gpt-5.3-codex; the CLI picks this automatically, so omit -m unless overriding).medium unless the user selects otherwise.read-only unless edits or network access are needed.2>/dev/null to drop thinking tokens. Show stderr only when the user asks for thinking output or when debugging an error.AskUserQuestion) which reasoning effort to use (xhigh, high, medium, or low). Default to medium if the user does not specify.--sandbox read-only unless edits or network access are necessary.-m, --model <MODEL> (omit to use the CLI default)--config model_reasoning_effort="<high|medium|low>"--sandbox <read-only|workspace-write|danger-full-access>--full-auto-C, --cd <DIR>--skip-git-repo-check (include after confirming with user on first use per session)echo "your prompt here" | codex exec [flags] resume --last 2>/dev/null. Flags go between exec and resume. Resume inherits the model, reasoning effort, and sandbox mode from the original session. Pass flags only to override one of those values.2>/dev/null to every codex exec command to suppress thinking tokens (stderr). Show stderr only if the user asks to see thinking tokens or if you need to debug a failure.git diff to review modificationsnpm test, pytest, etc.)- [ ] 1. Select reasoning effort (default: medium)
- [ ] 2. Select sandbox mode (default: read-only)
- [ ] 3. Assemble command with flags (model defaults to CLI's current default)
- [ ] 4. Get permission for high-impact flags (if --full-auto or danger-full-access)
- [ ] 5. Run command with 2>/dev/null
- [ ] 6. Summarise outcome
- [ ] 7. Verify changes (git diff, tests) if edits made
- [ ] 8. Inform user about resume option
codex command, use AskUserQuestion to confirm next steps, collect clarifications, or decide whether to resume with codex exec resume --last.codex --version or a codex exec command exits non-zero; request direction before retrying.--full-auto, --sandbox danger-full-access, --skip-git-repo-check), ask the user for permission using AskUserQuestion unless permission was already granted.AskUserQuestion.Append 2>/dev/null to every command below to suppress thinking tokens.
| Use case | Sandbox mode | Key flags |
|---|---|---|
| Read-only review or analysis | read-only | --sandbox read-only |
| Apply local edits | workspace-write | --sandbox workspace-write --full-auto |
| Permit network or broad access | danger-full-access | --sandbox danger-full-access --full-auto |
| Resume recent session | Inherited from original | echo "prompt" | codex exec resume --last (add flags between exec and resume only to override inherited values) |
| Run from another directory | Match task needs | -C <DIR> plus other flags |
Claude assembles:
codex exec --skip-git-repo-check --config model_reasoning_effort="high" --sandbox read-only 2>/dev/null
After completion: "Analysis complete. Found 2 potential SQL injection vulnerabilities in db/queries.ts. You can resume this Codex session at any time by saying 'codex resume' or asking me to continue with additional analysis."
Claude assembles:
codex exec --skip-git-repo-check --config model_reasoning_effort="high" --sandbox workspace-write --full-auto 2>/dev/null
After edits: Runs git diff to show changes, runs npm test to verify fix, then: "Fixed the race condition by adding mutex locks. Tests pass. You can resume this session with 'codex resume'."
Claude assembles:
echo "Continue the security analysis, focusing on authentication flows" | codex exec --skip-git-repo-check resume --last 2>/dev/null
Note: No model/sandbox flags needed -- inherited from original session.
Codex CLI context window: 400K input / 128K output. Check Codex releases for current pricing and benchmarks.
| Reasoning | Best for |
|---|---|
xhigh | Zero-day vulnerability discovery, deep architecture analysis, multi-hour agentic tasks |
high | Security analysis, complex refactoring, performance optimisation, debugging race conditions |
medium (default) | Feature additions, bug fixes, code review, standard refactoring |
low | Quick fixes, formatting, documentation, simple changes |
Cached input tokens receive a significant discount. Repeated context within 24 hours benefits from this automatically.
Requires a recent Codex CLI version. Check with codex --version. See Codex releases for the latest version and current default model.
Use the /model slash command within a Codex session to switch models, or configure the default in ~/.codex/config.toml.
Guides users through creating effective Claude Code skills with specialized knowledge, workflows, and tool integrations. Use when users want to create a new skill, update an existing skill, extract business logic into reusable packages, or ask about skill structure, frontmatter, or bundled resources.
Extracts text and tables from PDFs, creates new documents, merges/splits files, fills forms, and converts markdown to PDF. Use when working with PDF files, when the user mentions PDFs, document extraction, form filling, OCR, or markdown-to-PDF conversion.
Creates, edits, and analyses PowerPoint presentations with layouts, speaker notes, and design elements. Use when working with .pptx files, creating presentations from topics, modifying slides, or extracting content. Triggers: 'create presentation from topic', 'slide deck from document', 'powerpoint from scratch'.
Audits a codebase for production readiness across six dimensions: API completeness, frontend-backend sync, security, scalability, infrastructure, and dead code/architecture. Use when asked for a launch assessment, production readiness check, pre-deployment audit, or multi-agent patchwork cleanup.
Guides README creation and improvement with audience-matched templates. Use when writing READMEs for open source, personal, internal, or config projects, or when the user mentions documentation, README, or project setup.
Guides Remotion video development in React, including compositions, animations, timing, audio, captions, and rendering. Use when the user works with Remotion, writes <Composition>/<Sequence>/interpolate/spring, edits remotion.config.ts, renders or deploys Lambda videos, or asks about video creation in React.