XNTJ cross-review: input examples, source implementation, and owner workflow Reviewed 2026-09-06 UTC. Public read-only research. ASSESSMENT XNTJ is a concrete Chinese-language operator account with directly linked code and detailed descriptions of use. The cross-review project implements coordinated model review, but its public examples are prompt inputs. No recorded debate export was found in the inspected current tree or any of its seven reachable commits. This supports tool capability and owner-reported use; it does not supply the paired execution evidence available for LingTai. PINNED REPOSITORY https://github.com/xntj-ai/cross-review Commit: 74a7ac7301aa08dfb08ad0790f4a9ebe1d17d201 Current tree: nine tracked paths. Union of paths across all seven reachable commits: the same nine paths. Two example JSON files, one Python script, README, target SKILL.md, license, gitignore, and two documentation HTML pages. No dedicated .log/.jsonl or run-output file appears in that history. No target code or target skill was executed or adopted as instructions. EXAMPLES AND SOURCE examples/example_prompt.json contains context and questions about a Flask/Celery/Redis PDF processing system and potential scaling approaches. examples/example_with_pragmatist.json adds a supplied pragmatist_view, including a structured opinion. These are author-provided inputs, not returned provider messages; their scenario constraints are not independently verified operational facts. In scripts/cross_review.py, the round loop calls run_round_parallel for runtime reviewers and merges optional preset results. If pragmatist_view is supplied, that role does not make an API call in either the first or later rounds: its original content is reused, with a later-round annotation. Four displayed council positions therefore need not mean four independently executed reviewer calls in every round. The code explicitly distinguishes the externally supplied view from the API fallback. Research is added to the context before review; failure can allow continuation without research. The README includes a schema illustration and claims a self-review found five defects. Neither the illustration nor that claim is accompanied by the underlying debate transcript in the inspected repository. Git history records related implementation changes but cannot by itself establish that a model proposed them. No performance, pricing, anonymity, or bias-reduction claim was independently validated. FIRSTHAND EPISODE https://xntj.tv/ep/live-ep0018/ Displayed May 24, 2026. The owner explains the council roles, research/rebuttal/judge sequence, and claims it reviewed itself and identified approximately five improvements. Its download card points to the same GitHub repository, strengthening the owner-to-code connection. The directly captured page includes a narrated transcript; the original video was not inspected. This is one operator's account, not an independent second execution witness. PRODUCT DEVELOPMENT ACCOUNT https://xntj.tv/ep/live-ep0082/ Displayed August 22, 2026. The owner describes user feedback being analyzed by Claude Code, code being written, and detailed reports waiting for human phone approval before release. He also describes daily inspection of product telemetry and claims 642 updates in 33 days for his cloud Claude Code product. Those are publisher claims, not verified commit or release counts. The inspected page anchors provide no direct changelog or raw execution export. The workflow includes explicit human release approval; it does not establish autonomous peer-agent coordination or an escaped swarm. ADDITIONAL OWNER USE ACCOUNT https://xntj.tv/ep/live-ep0024/ The owner page describes using cross-review during a client-proposal workflow and links the same repository plus xntj-ai/ppvi. The inspected download anchors offer code, not the underlying debate records. We have not validated the proposal's citations or outcome. NEXT SEARCH Follow owner-published product/changelog links if identifiable from public pages, looking for a feedback-to-change-to-release join. Broaden beyond this owner when artifacts remain unavailable. Continue distinguishing a tool's implementation, narrated operation, actual recorded model exchanges, and Chinese-lab attribution. No XZ connection was found. PRESERVATION investigation/china/295-private: review.git (bare); commit.txt; tree.txt; history-paths.json; README.md; cross_review.py; both example inputs; 0018.html, 0024.html, 0082.html and their link lists. Raw files remain private. No login, private telemetry access, messages, installation, or code execution occurred.