codex-mcp-setup — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited codex-mcp-setup (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
使用者希望 Codex 使用與 Claude-side Polaris workflows 相同的 external integrations 時，使用此 skill。
執行：
bash scripts/sync-codex-mcp.sh --dry-run這會檢查 baseline servers 是否已存在：
claude_ai_Atlassianclaude_ai_Slack執行：
bash scripts/sync-codex-mcp.sh --apply --login注意：
--login 可能會在瀏覽器開啟 interactive OAuth。codex mcp login <name>。若使用者希望 Codex 使用 Calendar，使用 streamable server URL：
bash scripts/sync-codex-mcp.sh --apply --login \
--with-google-calendar-url "<MCP_SSE_URL>" \
--google-calendar-token-env "<TOKEN_ENV_VAR>"執行：
mise run cross-runtime-sync
bash scripts/mechanism-parity.sh --strict
bash .claude/skills/codex-mcp-setup/scripts/polaris-codex-doctor.sh摘要需包含：
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.