Menu
Translates task requirements into Codex CLI commands. Used by codex-driver agent to execute coding tasks via OpenAI Codex.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Translates task requirements into GitHub Copilot CLI commands. Used by copilot-driver agent to execute coding tasks via Copilot.
Translates task requirements into Cursor CLI commands. Used by cursor-driver agent to execute coding tasks via Cursor.
Intelligently routes and delegates coding tasks to the best AI agent (Codex, Cursor, Gemini, Copilot). Use /delegate <task> to automatically pick the optimal agent based on task type and complexity.
Translates task requirements into Gemini CLI commands. Used by gemini-driver agent to execute coding tasks via Google Gemini.
"Structured brainstorming with research-driven exclusion zones and shape uniqueness enforcement. Forces divergent thinking through volume and a hard constraint: no idea can take the same shape as any prior art or any previous idea. Use when exploring solutions to a problem, designing features, or when the obvious approach might not be the best one."
| name | codex |
| description | Translates task requirements into Codex CLI commands. Used by codex-driver agent to execute coding tasks via OpenAI Codex. |
Subagents run with a minimal PATH. Always include homebrew path:
export PATH="/opt/homebrew/bin:$HOME/.local/bin:$PATH" && codex <args>
Always apply these to every codex exec command:
--skip-git-repo-check — required for all commands2>/dev/null — suppresses thinking tokens (omit only if debugging)--full-auto — required when using workspace-write or danger-full-access sandboxexport PATH="/opt/homebrew/bin:$HOME/.local/bin:$PATH" && codex exec --skip-git-repo-check --sandbox <MODE> [options] "<prompt>" 2>/dev/null
export PATH="/opt/homebrew/bin:$HOME/.local/bin:$PATH" && echo "<prompt>" | codex exec --skip-git-repo-check resume --last 2>/dev/null
Note: When resuming, do not include model/sandbox flags — the session inherits its original settings. Flags must go between exec and resume.
| Task Type | Mode | Notes |
|---|---|---|
| Analysis, review, Q&A | --sandbox read-only | No file modifications allowed |
| Create or edit files | --sandbox workspace-write --full-auto | Standard for most coding tasks |
| Network access needed | --sandbox danger-full-access --full-auto | Confirm with user first |
When the calling agent specifies requirements, translate to flags:
| Requirement | Flag | Notes |
|---|---|---|
| Default | -m gpt-5.2-codex | Optimized for code tasks |
| General-purpose | -m gpt-5.2 | Non-code or mixed tasks |
| Complexity | Flag | Notes |
|---|---|---|
| Complex / multi-step | --config model_reasoning_effort="xhigh" | Architectural decisions, large refactors |
| Standard (default) | --config model_reasoning_effort="high" | Most coding tasks |
| Simple | --config model_reasoning_effort="medium" | Straightforward edits |
| Trivial | --config model_reasoning_effort="low" | Quick fixes, formatting |
If not specified, use defaults: gpt-5.2-codex with high reasoning.
Report to user: "You can resume this Codex session by saying 'codex resume'."
danger-full-access: confirm with user unless pre-authorized