Menu
Asks Codex CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding tasks.
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
Guided development workflow that orchestrates planning, review, implementation, testing, and rule maintenance. Use this skill whenever the user wants to develop a feature, fix a bug, refactor code, or make any code changes following a structured process — even if they don't explicitly mention "workflow" and simply describe what they want built or fixed.
Check code changes for .claude/rules/ compliance. Use this skill when you need to verify that code changes follow project coding rules, whether as part of dev-workflow or standalone. Triggers on: rule compliance check, rules review, verify conventions, check coding standards. Best suited for hard rules (naming, imports, placement, explicit prohibitions); intent-style rules are checked on a best-effort basis.
Consult with a peer engineer for plan review, code review, implementation discussions, or problem-solving brainstorming. Use when you need a second opinion, want to validate your approach, or check for overlooked issues.
Review uncommitted diff for content unsuitable for publication to a public repository — secrets/credentials, user-specific absolute paths, internal-only URLs/hostnames, and personal identifiers. Each iteration dispatches a fresh subagent that returns findings; the main thread applies the subagent's mechanical fixes and re-dispatches until the subagent declares no remaining findings or max iterations is reached. Non-interactive — no user prompts. Use as a final gate before publishing changes; designed to be called from non-interactive routines such as dev-workflow's hooks.on_complete or dev-workflow-triage's per-Finding sub-flow.
Refactor verbose or unnatural natural-language prose — code comments, test descriptions, docstrings, user-facing text — into concise, native-sounding prose in a configured target language, using a sonnet subagent by default. Two modes: file mode rewrites a file's target-language prose in place; text mode returns the refactored text. Preserves code, identifiers, and proper-noun terms while translating ordinary technical vocabulary into the target language. Non-interactive — no user prompts. Use after generating prose with a model prone to verbosity, or to polish text before presenting it.
Review changed code for reuse, quality, and efficiency, then apply cleanup edits. Dispatches a fresh host-provided reviewer per iteration when available; the main thread applies mechanical edits and re-dispatches until no further edits remain. Non-interactive — no user prompts. Use after implementation as a code-cleanup pass complementary to correctness review.
| name | ask-codex |
| description | Asks Codex CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding tasks. |
| allowed-tools | Bash(codex *) |
Executes the local codex CLI to get coding assistance.
Note: This skill requires the codex CLI to be installed and available in your system's PATH.
Run a single query with codex exec:
codex exec "Your question or task here"
| Option | Description |
|---|---|
-m MODEL | Specify model |
-C DIR | Set working directory |
--full-auto | Enable automatic execution with workspace-write sandbox |
For all available options, run
codex exec --help
Use exec resume --last to continue the most recent session with a follow-up prompt:
codex exec resume --last "Your follow-up prompt"
Note:
exec-level flags such as-Cand--full-autoare not accepted byexec resume— the resumed session inherits the original session's working directory. To adjust the sandbox on resume, use-c sandbox_mode="workspace-write";-m MODELremains available.
Ask a coding question:
codex exec "How do I implement a binary search in Python?"
Analyze code in a specific directory:
codex exec -C /path/to/project "Explain the architecture of this codebase"
Use a specific model:
codex exec -m gpt-5.3-codex "Write a function that validates email addresses"
Let Codex make changes automatically:
codex exec --full-auto "Add error handling to all API endpoints"
exec subcommand--full-auto for automatic execution within sandbox constraints-C is specified