# Advise

> Ask Codex a read-only question with explicit model, effort, budget, and compact results.

- Skill: `borda/advise-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add borda/advise-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/borda/advise-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Borda (https://skillmd.com/u/borda)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/borda/advise-2

---


# Ask Codex for Advice

Parse `$ARGUMENTS`: required question; optional `model`, `effort`, `timeout-seconds`, `depth`, `run-id`, `workspace`. Reject empty question. Effort omitted: classify complete question, pass selected level explicitly. Preserve caller-supplied level. Tiers: `low` = narrow mechanical change or settled fact; `medium` = bounded implementation, diagnosis, or review; `high` = cross-file, adversarial, architectural, or security judgment; `xhigh` = unusually broad and consequential; `max` = explicit caller request only.

Run `python "${CLAUDE_PLUGIN_ROOT}/bin/bridge_call.py" advise --task "<question>"`; pass each supplied option separately. For quoted text you did not author, use scratch file + `--task-file <path>` instead of `--task`; mutually exclusive. Bridge uses read-only ephemeral Codex run; default soft budget 120 seconds. Never resume advice. Follow up with fresh request containing prior `remaining` items.

Return compact JSON envelope. Preserve workspace-relative `transcript_path` and `incident` references. Do not copy raw transcript or verbose peer `details` into conversation.