Evidence-driven deep research agent for Claude Code and Codex/ChatGPT Work, with schema v2, claim-ledger audits, safe screenshots, and strict QC.
This repository also configures its own agents. See what research-agent tells them →
Agent Claude Code
A report-editing agent that turns an assembled research draft into a clear final report for decision-makers. It only reorganizes, shortens, and rewrites material already in the draft.
Agent Claude Code
A research sub-agent that investigates one section of a larger research project and writes a sourced draft. It checks sources against one another and labels facts, opinions, disputes, judgments, and guesses.