← Back to list

weiwen-law-dsh

DeepSeek Harness Other Low risk

White-box causal guardrail for dsh: every tool call is adjudicated before execution along a deterministic causal logic chain — blocks destructive and credential-file operations, escalates repeated boundary violations, cuts faulting links until verified-fixed, and gives risk verdicts on un-auditable execution; runs fully local with zero API cost, plus 6 white-box self-check tools.

唯稳律白箱因果闸门:每个工具调用执行前沿确定性因果逻辑链裁决——拦截破坏性与凭据文件操作、对反复越界升级止损、故障环节切断至修复验证、不可审计执行给出风险判定;纯本地运行、零 API 成本,附带 6 个白箱自查工具。

How to install

DeepSeek Harness dsh plugin add github:Shaky77/weiwen-law-dsh

About

dsh-weiwen-law-plugin ✅ **Listed in awesome-dsh-plugin** — DeepSeek Harness 精选插件列表 **唯稳律通用因果引擎(白箱呈现)** —— 以 **DeepSeek Harness(DSH)** 的 Cordis 插件形态实现。 **框架定义:守真 · 稳态**(Keep Integrity & Steady State)。 - "守真"= 守护完整 / 真实(白箱不篡改 / 内 H 不可侵,对应 Integrity); - "稳态"= 系统存续优先(对应 Steady State)。 - "律 / Law" 为框架名后缀,**非**定义第三部分。 > 框架完整定义与哲学推导见基础版仓库(冻结门面),本仓为工程插件实现,不展开框架推导。 --- 30 秒看懂 本仓库把唯稳律因果框架做成 DSH 的插件:给跑在 DSH 上的 AI Agent 挂一套**白箱护栏**—— AI 每次动手前被**校验**,踩红线被**拦**,出错被**切断保活**; 同时把"状态 / 边界"暴露成**可查询工具**,AI 能自查、你能审计。 一句话:框架本体是"通用因果引擎(白箱呈现)","白箱审计 / 内生风控"是它的呈现姿态与适配场景后进化出的内生属性。 它做什么 **白箱自查**(呈现姿态):稳态储备记账、内 H 边界(不可侵…

Recommendation signals

47 Tool quality · Based on stars, downloads, maintenance, security and docs
User interest · Adjusted by in-site views, install copies and download clicks
47 Overall
0views
0unique visitors
0install copies
0download clicks
0outbound clicks

Meta

License
AGPL-3.0
Language
HTML
GitHub stars
1
mo. downloads
Last push
2026-08-27
Created
2026-08-19

Links

GitHub ↗ Report issue ↗

Basic safety check

Findings
curated 收录但无 npm 包/安装命令
Sources
curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics
ai, causality, dsh-plugin, harness, risk-control, white-box

Related plugins

DeepSeek Harness New
Score67

dsh-auth-gateway

xbzbing/dsh-auth-gateway

Password + TOTP two-factor authentication gateway for the dsh web UI: every HTTP request and WebSocket upgrade is refused until login, with per-source lockout, global rate limits and one-time backup codes.

☆ 8 ↓ 1.4K Other
DeepSeek Harness New
Score66

dsh-approval-llm

Letter2025/dsh-approval-llm

Model-based permission approval: an approval-request answerer backed by a separate reviewer model.

☆ 8 ↓ 781 Other
DeepSeek Harness New
Score63

dsh-auto-review

PerryLink/dsh-auto-review

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

☆ 112 ↓ 1.1K Other
DeepSeek Harness New
Score62

dsh-yolo-mode

SeverusZh/dsh-yolo-mode

LLM auto-approval for sandbox escalation requests, with presets and a fail-closed fallback.

☆ 3 ↓ 322 Other