claudex

ClaudeX

Claude Code skills that put a second model — and an enterprise-grade research pipeline — in your terminal.

ClaudeX ships these Claude Code skills:

Skill	What it does
/claudex:think	Brainstorming with an automatic Codex second opinion on every clarifying question. Two models pressure-test the framing of each question instead of one.
deep-research	Subscription-only multi-agent deep research — a port of NVIDIA AI-Q's deep-research core that runs entirely on Claude Code (native WebSearch/WebFetch + parallel subagents), with deterministic citation verification. No server, no API keys.
/claudex:setup	One-command bootstrap of claudex's dependencies — installs the Codex plugin and superpowers, then verifies the Codex CLI. Run it once after installing claudex.
/claudex:email	Broadcast a brainstorm question to a panel. Send-only: pushes the current question + a short context snapshot to people in ~/.claude/claudex/panel.json so they can read on their own device during a screen-shared meeting and reply by email or aloud.
/claudex:build	Codex-driven build orchestrator. Takes an approved spec to a PR: Codex writes the plan and the implementation, a Codex reviewer and a Claude reviewer independently attack each artifact, and a fresh Codex agent reconciles them into one verdict (go / fix-go / fix-review). Claude conducts; the run ends at an opened PR.

---

/claudex:think — Codex second-opinion brainstorming

/claudex:think arms a lightweight gate, then runs normal brainstorming. A PreToolUse hook intercepts each AskUserQuestion call, sends the drafted question to Codex (read-only, via the Codex plugin's runtime), blocks the question, and feeds Codex's critique back to Claude. Claude then presents:

Codex says: (Codex's critique, verbatim) My take: (1–3 sentences — agree/disagree, folding in any fixes)

…and re-issues the (possibly revised) question, which passes through. Claude never has to remember to ask Codex — the hook enforces it.

Design before implementation is also guarded. While a think session is armed, extra PreToolUse hooks block edits to code and to protected instruction files (CLAUDE.md/SKILL.md/AGENTS.md/GEMINI.md), block implementation skills (TDD, executing-plans, …), and refuse Bash commands that write code or tamper with the gate marker — so Claude can't quietly skip brainstorming and start coding. Design/spec/plan markdown stays writable, and the gate opens automatically once brainstorming has run and writing-plans is invoked. Turn it off with enforceImplementationGate: false or the kill switch.

This is a cooperative-agent guardrail, not a security sandbox. It fails open and is heuristic on the shell path: read-only exploration passes, common write patterns are blocked, but a determined bypass (exotic shell, or write-capable MCP tools not covered by the matchers) is still possible. Its job is to interrupt the "just edit the file" reflex, not to contain an adversary.

Requires the Codex plugin (openai/codex-plugin-cc) for the Codex runtime and superpowers (anthropics/claude-plugins-official) for the brainstorming flow. The quickest way to get both is /claudex:setup (see below).

Configuration

Runtime config lives at ~/.claude/claudex/config.json (created on first use; see config.example.json):

Key	Default	Meaning
enabled	true	Master switch for the gate.
failClosed	false	If true, a question is blocked when Codex is unavailable. Default fails open.
enforceImplementationGate	true	While armed, block edits to code and to protected instruction files (CLAUDE.md/SKILL.md/AGENTS.md/GEMINI.md) and block implementation skills until the design is approved and writing-plans runs. Design/spec/plan markdown stays writable.
effort	"low"	Codex reasoning effort for the critique.
ttlHours	6	The armed marker auto-expires after this many hours.
timeoutMs	180000	Max time to wait for Codex per question.

Kill switch: rm -f ~/.claude/claudex/armed (this session) disarms both the Codex question gate and the implementation gate; set {"enabled": false} in the config (globally); set {"enforceImplementationGate": false} to keep the Codex second opinion but stop gating edits/skills; or just tell Claude "solo" / "no codex".

---

deep-research — enterprise-grade deep research, fully on your subscription