Plugins

维修工单结算核对（按项目金额、配件工时合计与结算总额核对算术自洽，仅提示差异，不作出定性结论）

起诉状要素齐备性核对（按诉请、事实、证据、法条四要素核对文书齐备，仅提示差异，不作出定性结论）

Flags ICD coding pairs that need a coder's attention - dagger and asterisk combinations, combination codes - against GB/T 14396-2016 and published ICD usage notes. Reports the pairs it finds rather than resolving them; the coding decision stays with the coder.

公文流转与办理时限核对（按公开的公文处理规范核对环节完整性与时限，仅提示差异，不作出定性结论）

政策专报要素核对（按观点、依据、出处与建议核对专报齐备，仅提示差异，不作出定性结论）

原产地区域价值成分核对（按 RVC 定义式与门槛核对原产地判定自洽，仅提示差异，不作出定性结论）

Evidence-list completeness check: maps facts to evidence and reports gaps with rule IDs.

商品归类层级一致性核对（按章、品目、子目与商品编号的层级关系核对自洽，仅提示差异，不作出定性结论）

招标文件条款摘录核对（按出处与原文逐字核对摘录完整性，仅提示差异，不作出定性结论）

Checks supervision logs for cross-day continuity and for on-site supervision coverage, against GB/T 50319-2013 and other published documents. Reports gaps and coverage differences for a human to review.

出口管制物项核对（按管制清单、最终用途与许可证核对台账齐备，仅提示差异，不作出定性结论）

投标文件符合性预检（按招标文件逐条核对响应情况，仅提示差异，不作出定性结论）

质保期与索赔金额核对（按质保期月数与里程、索赔金额算式核对自洽，仅提示差异，不作出定性结论）

Checks a bid evaluation scoring matrix for internal arithmetic consistency: that each factor's maximum, the scores recorded and the total agree with each other. Reports the differences it finds; it does not judge whether the evaluation itself was correct or fair.

Drive the desktop and Chrome from DeepSeek Harness using the computer-use runtime inside the ChatGPT desktop application.

投标人资格条件核对（按资格条件与证明材料核对逐条响应，仅提示差异，不作出定性结论）

Remote companion for dsh-remote-desktop iframe control.

三重一大决策台账核对（按前置研究、会议审议与决议记录核对程序留痕，仅提示差异，不作出定性结论）

Cross-session memory for your dsh agent: remembered, recalled, and re-verified instead of assumed.

A little cat that wanders the DeepSeek Harness UI, walking along text edges, napping, teleporting, falling off ledges, and leaving poops you can clean up.

Solo murder-mystery (jubensha) in a session tab: the AI hosts the game and plays every other seat, each knowing only its own role book, while the player's seat stays yours — with a stage bar, a per-seat timeline, a clue page and a reveal that unseals the truth only at the end.

Reimplements the shut-down BSide: Olivia Lin letter API on loopback so the game client keeps sending and receiving letters: every incoming letter is delivered to one persistent DSH agent session, and the reply is written back to the local letter store.

Control surface for the dsh-lan-gate LAN gateway: a button beside Settings that shows whether the gateway is running and how many phones or tablets are waiting for approval, opens the loopback-only approval page in one click instead of typing its URL, and starts the gateway through its scheduled task first when it is not running. Not rendered on phone or tablet surfaces.

Removes sandbox_permissions / justification arguments that cannot widen the call's current sandbox mode, so calls no longer fail with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "danger-full-access" mode'. GPT models tend to fill these optional fields on every call and pick workspace-write, which is narrower than danger-full-access. Runs in tools/pre-execute: compares the requested mode with the mode the session's sandbox policy resolves, and drops the fields when the request is the same or narrower (also drops a lone justification). Also understands the values GPT carries over from Codex's own shell tool: null, empty and use_default are treated as no request, and in a danger-full-access session any value (including require_escalated) is dropped because nothing is wider. Real widening requests, unknown modes and tools that do not advertise DSH's escalation schema are left to DSH core. Never widens permissions. Configurable tool list (default bash, pwsh, write, edit, run_code). Zero dependencies.