Research latest AI code agent models via web and update models_*.json configuration files.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add majiayu000/claude-skill-registry --skill aitask-refresh-code-models-beyondeye-aitasks-2 --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Aitask Refresh Code Models Beyondeye Aitasks 2?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-aitask-refresh-code-models-beyondeye-aitasks-2)More formats (shields.io, HTML) on the badges page.
---
name: aitask-refresh-code-models
description: Research latest AI code agent models via web and update models_*.json configuration files.
---
## Prerequisites
**If you are Codex CLI:** Read **`.agents/skills/codex_interactive_prereqs.md`** BEFORE proceeding.
## Source of Truth
This is a unified skill wrapper for Codex CLI and Gemini CLI. The authoritative skill definition is:
**`.claude/skills/aitask-refresh-code-models/SKILL.md`**
Read that file and follow its complete workflow.
**If you are Codex CLI:** For tool mapping and adaptations, read **`.agents/skills/codex_tool_mapping.md`**.
**If you are Gemini CLI:** For tool mapping and adaptations, read **`.agents/skills/geminicli_tool_mapping.md`**.
## Arguments
No arguments. Researches latest models via web and updates configuration.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
