Claude Skill

advise

Ask Claude Code a read-only question from Codex through the sandbox-external bridge.

LLM Mart · 0 points · 16 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download Borda-AI-Rig-plugins_bridge_cc-codex_codex-skills_advise-39e3a48.zip · 0 KB

borda/ai-rig 27 4 forks Apache-2.0 Updated 2d ago

Part of borda/ai-rig — 82 skills

Install

skills CLI npx skills add https://github.com/Borda/AI-Rig/tree/main/plugins/bridge_cc-codex/codex-skills/advise

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install borda-ai-rig@llmmart

Git git clone https://github.com/Borda/AI-Rig.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole borda/ai-rig collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Before asking, read User Questions.

Ask Claude Code for Advice

Call bridge_advise with required task; preserve caller-supplied model, effort, timeout_seconds, depth, and run_id. If effort absent, select and pass it: low for narrow mechanical or settled factual work; medium for bounded implementation, diagnosis, or review; high for cross-file, adversarial, architectural, or security judgment; xhigh for unusually broad consequential work; max only on explicit request. Never replace supplied effort.

MCP host binds its launch workspace. Return compact envelope; retain workspace-relative transcript_path and incident references, but never copy transcript-only peer details. Follow up with fresh call, never session resumption.

If status=blocked, open the JSON file referenced by incident; inspect its fault. For output-limit, report incomplete advice. Split by file, symbol, or independent question; use fresh read-only calls with bounded tool output. Reconcile every scope; name unanswered work. Never treat transcript fragments as answers.

Files (ai-rig)

SKILL.md 1.2 KB

---
name: advise
description: Ask Claude Code a read-only question from Codex through the sandbox-external bridge.
---

> Before asking, read [User Questions](../../rules/codex-user-questions.md).

# Ask Claude Code for Advice

Call `bridge_advise` with required `task`; preserve caller-supplied `model`, `effort`, `timeout_seconds`, `depth`, and `run_id`. If effort absent, select and pass it: `low` for narrow mechanical or settled factual work; `medium` for bounded implementation, diagnosis, or review; `high` for cross-file, adversarial, architectural, or security judgment; `xhigh` for unusually broad consequential work; `max` only on explicit request. Never replace supplied effort.

MCP host binds its launch workspace. Return compact envelope; retain workspace-relative `transcript_path` and `incident` references, but never copy transcript-only peer `details`. Follow up with fresh call, never session resumption.

If `status=blocked`, open the JSON file referenced by `incident`; inspect its `fault`. For `output-limit`, report incomplete advice. Split by file, symbol, or independent question; use fresh read-only calls with bounded tool output. Reconcile every scope; name unanswered work. Never treat transcript fragments as answers.