ClaudeX

Turn an approved spec into a merged-ready PR with Codex doing the writing. Claude conducts; Codex writes the plan and the implementation; a Codex reviewer and a Claude reviewer independently attack each artifact; a fresh Codex agent reconciles them into one verdict (go / fix-go / fix-review). Use when the user runs /claudex:build, or asks to build/implement an existing spec with Codex as the builder and an adversarial review loop.

Deep, multi-source, fact-checked research reports — entirely on the Claude subscription, no API keys. Plans a TOC + acceptance criteria, fans out parallel Task subagents that search the live web (native WebSearch/WebFetch), gap-fills weak sections, then synthesizes a long-form report with inline [n] citations and a Sources list whose every URL is DETERMINISTICALLY verified against URLs that actually appeared in search results (fabricated citations are dropped). A subscription-only port of NVIDIA AI-Q's deep-research core. Use when the user wants a thorough researched report, a literature/landscape/market scan, a cited comparison, or "deep research" / "research X for me". BEFORE invoking, if the question is underspecified (e.g. "what car should I buy" with no budget/use/region), ask 2-3 clarifying questions to narrow scope, then research the refined question.

Brainstorm a feature or design with an automatic Codex second opinion on every clarifying question. Use when the user runs /claudex:think, or asks for Claude+Codex collaborative brainstorming. Wraps superpowers:brainstorming.

Dual-model deep research with adversarial cross-audit. Claude and Codex each run their own deep-research skill independently on the same question, then each audits the OTHER's citations (claim-support: PASS/WEAK/FAIL → trust-score + verdict), and Codex synthesizes one trust-weighted final report with a disagreement ledger. All 5 notes (2 reports, 2 audits, 1 final) + an index land in a persistent Obsidian-style vault; the main session returns a concise bullet summary. Use for high-stakes questions, when the user wants dual-model / cross-verified research, or when a prior deep-research run came back mixed / unreliable. For ordinary research, use claudex:deep-research instead.

Broadcast the current brainstorm question plus a short context snapshot to a configured panel by email (SEND-ONLY), so people can read it on their own device during a screen-shared meeting and reply by email or aloud. Use when the user runs /claudex:email, or asks to "email the panel", "send this question to the panel", or "broadcast this to the panel". Reads recipients from ~/.claude/claudex/panel.json. Does not collect replies and does not modify claudex:think.

Use when the user runs /claudex:setup or asks to install/bootstrap claudex's dependencies (the Codex plugin and superpowers). Installs both plugins, then verifies the Codex CLI via codex:setup.