Deep Research

deep-research

A Claude Code plugin for rigorous web research using three independent LLM
families as cross-checkers, worktree-sandboxed for security, and
primary-source verified via mechanical URL + passage checks.

The single goal: produce research output you can actually trust to make
decisions on — by hardening against the failure modes single-pipeline LLM
research is known to produce (consensus hallucination, fabricated citations,
prompt injection from web content, CLI/API confabulation).

What it does

/research spawns one researcher agent in worktree isolation. The agent
then runs three parallel research streams:

1. Claude (you) — WebSearch + WebFetch
2. Gemini 3.1 Pro — via the agy (Antigravity)
   CLI, sandboxed (--sandbox)
3. GPT-5 — via OpenAI's codex CLI,
   sandboxed (-s read-only)

Each stream uses a different web-search backend (Google Search inside Gemini,
OpenAI's web tool inside Codex, Claude's WebSearch). After all three return,
the researcher triages four lists — Agreements / Gemini-only / GPT-only /
Conflicts — and resolves each one via primary-source verification before
including it in the final report.

The defense model is evidence weight > vote count. One cross-checker with
a primary-source URL that passes mechanical verification (URL resolves 2xx +
quoted passage actually appears in the fetched page) beats a two-way LLM
consensus with no source. Why this matters is documented in the literature
on consensus hallucination — when training corpora overlap heavily, LLM
agreement-without-evidence is a *weaker* signal than minority-dissent-with-
evidence (Shared Imagination, arXiv:2407.16604;
Till et al. 2025).

Defenses

Installation

This is a local Claude Code plugin. Drop it under your plugins directory and
enable it.

Restart Claude Code (or…