DSH插件商店 DSH-plugin store

DSH-PLUGIN STORE / LIVE CATALOG

DSH插件商店

聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。

已收录
6553
功能分类
11
更新时间
10/07 02:01
全部 6553 界面增强 408 Agent 与会话 549 开发工具 593 消息通讯 191 文件与数据 394 模型与 MCP 314 安全与治理 134 部署运维 206 生活娱乐 207 学习研究 80 其他 3477

22 个项目，匹配「approval」

安全与治理 插件

dsh-auto-review

PerryLink

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

ai-agent ai-agents ai-safety approval
233 2 10
3 天前
安全与治理 插件

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

ai-agent ai-agents ai-safety allow-deny-ask
118 3 9
3 天前
安全与治理 插件

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件

agent-harness agentic-ai ai-agents ai-safety
24 2 0
4 天前
安全与治理 插件

Make every agent edit approvable in DeepSeek Harness: full-diff review, per-file / per-block keep & revert, undo/redo.

ai-coding approval deepseek-harness diff
9 1 2
4 天前
安全与治理 插件

dsh-riskproof

onlyqzq

Risk-aware approval layer for high-risk AI Agent tool calls

agent-security dsh-plugin provenance tool-security
7 0 0
5 天前
安全与治理 插件

dsh-harness-jarvis

CroissanTTs

贾维斯 · 常驻桌面的悬浮窗桌面助手 / 桌面宠物 —— DSH Desktop 的粒子光球：快速审批权限、⌃⌥J 快速对话。A floating-window desktop assistant & desktop pet for DSH Desktop.

approval deepseek desktop-assistant desktop-pet
6 0 0
14 天前
安全与治理 插件

dsh-automode

log-li

Claude Code-style auto approval layer for DeepSeek Harness: deterministic rules + two-stage classifier, circuit breaker, fail-to-human. Shadow mode day one.

auto-approval deepseek-harness dsh-plugin
6 0 0
11 天前
安全与治理 插件

Automode for DeepSeek Harness: a fourth permission preset — full access with an LLM classifier as the only gate before every tool call.

automode deepseek-harness dsh dsh-auto-approval
3 1 1
19 天前
安全与治理 插件

DeepSeek Harness 自动审批插件：关键词 + 审核模型审核表。

approval auto-approve cordis deepseek-harness
3 1 3
23 天前
安全与治理 插件

dsh-yolo-mode

SeverusZh

dsh-yolo-mode - an LLM-powered auto-approval plugin for DeepSeek Harness sandbox escalations (built-in presets + custom permission levels, fail-closed)

approval deepseek-harness dsh dsh-plugin
3 0 0
10 天前
安全与治理 插件

Per-edit approval gate for DeepSeek Harness — red/green line diff review before write/edit/stream operations · DSH 插件：逐操作审批门，write/edit/stream 执行前进行红绿行级 diff 审查

approval client-plugin code-review cordis
3 0 0
10 天前
安全与治理 插件

dsh-autogate

wangxing-git

DeepSeek Harness 自动审批插件：在 workspace-write 沙箱之上叠加确定性规则 + LLM 安全审批，自动模式不放宽沙箱、fail-closed。 Safe auto-approval for DeepSeek Harness — deterministic rules + LLM review on top of the workspace-write sandbox. Auto mode without ever granting full-access.

auto-approval deepseek deepseek-harness dsh
3 0 1
8 天前
安全与治理 插件

dsh-auto-review

Jelee0145

Codex-style automated approval review for DeepSeek Harness: an isolated reviewer subagent decides sandbox escalations by intrinsic risk and user authorization. Community Beta — not an official DeepSeek AI plugin.

auto-review deepseek-harness dsh dsh-plugin
2 0 0
1 个月前
安全与治理 插件

Deterministic fail-closed tool-call authorization for DSH with evidence: allow/block/ask policy gate plus approval-chain deferral.

agent-safety agent-tooling ai-safety deepseek-harness
2 0 0
1 个月前
安全与治理 插件

dsh-approval-ai

ang-XWBWZ

AI approval answerer for DeepSeek Harness (DSH) using the unified LLM route with fail-closed policy checks.

agent-harness approval cordis deepseek-harness
2 0 0
1 个月前
安全与治理 插件

dsh-approval-explain

Martlet-Tech

Explain what a pending dsh approval will actually do, with one LLM call: an Explain button beside Allow/Reject in the DeepSeek Harness Web GUI.

ai-agent approval deepseek-harness dsh
1 0 0
16 天前
安全与治理 插件

The deny-by-default governance kernel for AI agents — permissions, L0–L4 guardrails, human approvals and an immutable audit chain as an Apache-2.0, framework-neutral library. Gate LangGraph / CrewAI / n8n / Dify or plain scripts in three lines.

agent-governance ai-agents audit-trail digital-employees
1 0 17
10 天前
安全与治理 插件

按单命令前缀自动放行 DSH 沙箱提权请求, 含管道与链式的命令一律转人工审批.

approval deepseek-harness dsh dsh-plugin
1 0 0
10 天前
安全与治理 插件

dsh-vault-wall

lxwallac

DSH (DeepSeek Harness) plugin that hides or blocks sensitive filesystem paths from AI agents — privacy, sandboxing, guardrails & human-in-the-loop approval for Node.js

access-control ai-agent deepseek-harness dsh
1 0 0
24 天前
安全与治理 插件

DeepSeek Harness 审批守护者：权限请求先由审查模型裁决。内置 System One 决策 API 后端（TypeSafe Jev / 硅基流动 systemone / 自部署 Laya）、onLowConfidence 低置信度策略与 allowRules 免审白名单。fork 自 gbthui/dsh-auto-review。

ai-agent approval auto-review cordis
1 0 0
8 天前
安全与治理 插件

dsh-guard

KouzakiUmi

DeepSeek Harness 安全插件集：文件审计与会话回滚、可配置审查模型的自动审批；两个 bundle 可独立安装，设置由宿主管理。

agent-safety ai-agent approval audit
0 0 0
3 天前
安全与治理 插件

dsh-approval-review

LAwLi3tCoding

Codex-style agent auto-approval for DeepSeek Harness: an independent reviewer model decides allow/deny on the approval answerer chain, fail-closed, with a rationale for every decision (refusals and allows) in a dedicated Approvals tab. · 替我审批：独立复核模型裁决，fail-closed，每次审批留详细理由。

ai-safety approval auto-review cordis
0 0 0
19 天前