Skill254 repo starsupdated 2mo ago

sibyl-codex-reviewer

The sibyl-codex-reviewer skill generates independent third-party code review feedback by leveraging OpenAI's Codex model through the Sibyl system's orchestration layer. Use this skill when you need alternative AI perspectives on code quality, functionality, or design patterns within a specified workspace, with optional model customization and automated execution policies for non-interactive review workflows.

View source Repository: AutoResearch-SibylSystem

Install in Claude Code

Copy

git clone --depth 1 https://github.com/Sibyl-Research-Team/AutoResearch-SibylSystem /tmp/sibyl-codex-reviewer && cp -r /tmp/sibyl-codex-reviewer/.claude/skills/sibyl-codex-reviewer ~/.claude/skills/sibyl-codex-reviewer

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

!`SIBYL_WORKSPACE="$ARGUMENTS[0]" .venv/bin/python3 -c "from sibyl.orchestrate import render_skill_prompt; import os; ws = os.environ.get('SIBYL_WORKSPACE', ''); print(render_skill_prompt('codex_reviewer', workspace_path=ws))"`

AGENT_NAME: sibyl-codex-reviewer
AGENT_TIER: sibyl-light
SIBYL_ROOT: /Users/cwan0785/sibyl-system

Workspace path: $ARGUMENTS[0]
MODE: $ARGUMENTS[1]
Codex model override: $ARGUMENTS[2] (optional)

## Codex MCP 调用规范

每次调用 `mcp__codex__codex` 时：
- 若提供了 `Codex model override`，则显式传 `model: $ARGUMENTS[2]`
- 若未提供，则不要传 `model` 参数，使用 Codex MCP 默认模型
- 设置 `approval-policy: "never"` 以实现自动化执行