linxichen/dsh-rigorquant

Name: linxichen/dsh-rigorquant
Author: linxichen

Plugin插件 Native原生 ⭐ 6 MIT Data & Analysis数据与分析

为Deepseek工具包增加能力，以进行严谨的量化金融工作

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This repository is a native DSH plugin that provides a preconfigured multi-agent research preset for unattended empirical and computational mathematics work focused on economics, finance, portfolio optimization, and simulation. It ships with a DSH bundle manifest in its package.json, making it directly installable and discoverable in the DSH plugin ecosystem. The preset splits a single DSH session into context-isolated roles for eight different agents, each with specific responsibilities to enforce rigorous research workflows that prevent agents from verifying their own work and require all claims to be proven with concrete evidence.

The workflow is designed for researchers working on open computational problems in quantitative finance and computational economics who value rigorous, multi-agent validation of mathematical claims. After an explorer proposes candidate methods, an off-grid thinker works in isolation to develop derivations using tools like SymPy, NumPy, and mpmath, with no access to other agents’ results or external data. Two independent checkers then re-derive core closed forms and bounds from first principles, before an adversary eliminates invalid candidates via counterexample, and a meta-validator checks that all required evidence is present before numerical implementation begins.

This plugin is released under the permissive MIT open source license, and includes a built-in test suite for the core meta-validator script. The test suite includes a deliberately forged invalid study that the validator must fail, to ensure the honesty of the validation gate. The project enforces a 95% minimum line coverage requirement for the validator via a git pre-commit hook, which users can enable by running ./install.sh or manually setting git’s core.hooksPath to .githooks. Users need to have uv installed to sync dependencies and run the test suite locally, and CI also runs the same coverage check to enforce this requirement.

dsh-rigorquant是专为DeepSeek Harness开发的原生插件，面向经济学、金融领域的无人值守计算与经验数学研究任务，能够将单个DSH会话转换为上下文隔离的多智能体研究实验室。它预设了多个分工明确的智能体角色，包括并行探索者、离网思考者、校验者、对手验证者等，遵循生产者不得校验自身工作的核心原则。

它适用于需要严谨验证的计算金融、投资组合优化、数值模拟等研究任务，完整工作流包含提出候选方法、离网推导、闭式解重推导、反例排除、四步校验、元验证多个环节，只有通过所有校验的研究才会进入数值实现阶段。研究人员只需要在单个会话内发起任务，无需跨会话自主运行，遇到终止点仅需人工确认继续即可重新启动流程。

该插件采用MIT许可开源，包含一个元验证脚本rq_check.py，会自动检查研究产出的证据完整性，缺少推导内容或未通过编译的结果都会被拦截。项目自带测试套件，要求验证脚本的测试覆盖率不低于95%，未通过覆盖率校验的代码无法提交。用户安装后可以通过启用git预提交钩子来自动执行这个校验规则。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-rigorquant（linxichen/dsh-rigorquant）
仓库：https://github.com/linxichen/dsh-rigorquant
本站详情页：https://www.yhbd.top/plugins/linxichen-dsh-rigorquant/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 6 · 最近提交 2026-10-01 · 主语言 Python

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

Only 6 stars - very few users, little community feedback星标只有 6，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add dsh-rigorquant

把 linxichen/dsh-rigorquant 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

24.2 KB · 缓存于 2026-10-01 22:10:57 · 24.2 KB

dsh-rigorquant

English | 简体中文

Edgeworth box with contract curve and Pareto optimum

_{Edgeworth box — hand-drawn in
TikZ, no AI-generated imagery}

Unattended-within-a-session, long-running empirical/computational mathematics research for DeepSeek Harness — economics, finance, portfolio construction/optimization, simulation, computational econ/finance.

RigorQuant is an agent preset + bundled skills that turns one DSH session into a context-isolated multi-agent research lab:

Parallel explorers propose candidate methods (explorer-<n>, blank context).
An OffGridThinker (offgrid-<n>) works off the grid when a route must be isolated: raw model intelligence plus compute tools (sympy, numpy, mpmath, Lean checkers) — no web, no literature, no other agents' results.
A ground-truth track re-derives the analytic closed forms, invariants, and bounds for simplified cases — twice, by different means (two independent fresh doublechecker-<n> teammates).
An adversary eliminates routes by counterexample only.
A four-part check battery (closed-form equality, exact invariants, analytic bounds, statistical hardening) runs BEFORE numerical implementation.
A meta-validator (rq_check.py) refuses a PASS whose evidence is missing: empty stage outputs, an empty derivations/, a registry with no audit-referenced passed route, or deliverables that do not compile. Its evidence checks read the audit record, not study.json — a study may not vouch for itself.
Fixed-seed + LLN conventions for stochastic work.
A jacobian MCP escalation lane (opt-in; Lean as a manual external lane) settles proof-critical claims before implementation.
PASS → auto-implement and proceed; BLOCKED → 3 rounds of the same gap → strongest derivation + exact gap; BUDGET → 5 rounds → checkpoint + report.

The operating pattern adapts Shanmu Jin's Crouzeix-conjecture run (prompt, Lean audit) and Terence Tao's blueprint/equational-theories projects to numerical work. Full design record: docs/architecture.md.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 linxichen/dsh-rigorquant 的 README.md。在 GitHub 查看原文 →