Find the right plugin

Only repositories whose manifest declares dsh.bundle.patch.

Manifest verified

sandbaseai

sandbase-harness

Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a native DeepSeek Harness bundle over stdio MCP.

Security588

Manifest verified

NanmiCoder

dsh-auto-mode

Safe automatic permissions for DeepSeek Harness.

Security53

Manifest verified

omdsh-dev

dsh-custom-tool

Create and manage sandboxed JavaScript tools for DeepSeek Harness with a Monaco editor and model-driven tool lifecycle.

Security24

Manifest verified

Anionex

dsh-computer-use

为 DeepSeek Harness 提供电脑控制插件：新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入（目前支持macos）｜Accessibility-first macOS Computer Use bundle for DSH with fresh observations, stale-state rejection, scoped permissions, and safe input.

Security21

Manifest verified

dhicoc

dsh-reverse-skill

Complete reverse-skill (85 SKILL.md) as a DeepSeek Harness (dsh) Cordis plugin — reverse engineering, authorized pentesting and security research skill pack.

Security13

Manifest verified

omdsh-dev

dsh-security-audit

DSH 本机安全审计插件：配置/插件来源/会话/网络暴露面，只读脱敏风险报告

Security12

Manifest verified

Zhenyu98

dsh-context-doctor

DSH 上下文注入审计插件：统计 AGENTS.md 指令链/技能目录/工具 schema 的 token 成本，检测重复与冲突；Web UI 圆环面板 + context_audit 工具。Context Doctor for DeepSeek Harness: audit instruction-chain / skill catalog / tool schemas token cost.

Security9

Manifest verified

w2112515

dsh-plugin-development

Portable Agent Skill for developing and auditing DeepSeek Harness plugins, with an optional profile-installable DSH bundle adapter.

Security8

Manifest verified

timeance

dsh-approve-for-me

DeepSeek Harness plugin for rule-gated automatic sandbox approval with optional LLM review, one-time grants, fixed high-risk checks, and native human fallback.

Security7

Manifest verified

ZK-Andy

dsh-continual-evolve

Continual self-evolution plugin for DeepSeek Harness: versioned, auditable, rollback-safe harness state refined from session trajectories, with a benchmark-driven validation loop.

Security6

Manifest verified

tensorlakeai

dsh-tensorlake-sandbox

A deepseek harness plugin for tensorlake sandbox

Security5

Manifest verified

Letter2025

dsh-approval-llm

Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model

Security5

Manifest verified

nanshan1995

DSH-Plugin-Market

DeepSeek Harness 插件市场：精选目录 + GitHub 实时浏览、中英翻译搜索、安装前静态安全审计闸门。Plugin market for DeepSeek Harness with a pre-install security audit gate.

Security4

Manifest verified

MicroMilo

upstream-radar

DSH plugin security and dependency monitoring for DeepSeek Harness: exact vulnerable paths, breaking updates, and Agent follow-up.

Security4

Manifest verified

Jiao-XXX

dsh-auto-approve

为 DeepSeek Harness 增加介于 Workspace Write 与 Full access 之间的自动批准权限档，危险或不确定操作仍转人工审批。An auto-approval permission preset between workspace-write and full access for DeepSeek Harness.

Security4

Manifest verified

030611

qiushi-dsh-evidence-audit

Observe-only hash-chained evidence receipts for DeepSeek Harness

Security4

Manifest verified

bwndlct

dsh-session-audit

Session execution analytics and audit reports for DeepSeek Harness — see how your agent actually worked

Security4

Manifest verified

jkrandom-sudo

dsh-plugin-audit

Security audit for DeepSeek Harness plugins: static permission profile with file/line evidence + a runtime sentinel gating credential access and unknown-host egress · DSH 插件安全审计：静态权限画像（附文件/行号证据）+ 运行时哨兵，触及凭证或向未知主机外发数据时先请你批准

Security4

Manifest verified

PerryLink

dsh-auto-review

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).

Security3

Manifest verified

slywalker2006

dsh-passwords

dsh-passwords: DeepSeek Harness login gateway - first-run setup, at-rest encryption, brute-force lockout, audit log, HTTPS

Security3

Manifest verified

yunhuantian

dsh-plugin-hub

Plugin Store for DeepSeek Harness (DSH): a graphical app-store inside the Harness Web UI — browse, search and one-click install GitHub dsh-plugins (topic:dsh-plugin / #dsh-plugin repos), with local ratings, dependency impact graphs, audit logging and a plugin scaffold guide.

Security3

Manifest verified

PerryLink

dsh-permission-rules

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.

Security3

Manifest verified

PerryLink

dsh-memento

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)

Security3

Manifest verified

agentic-control-plane

dsh-acp-plugin

Agentic Control Plane for DeepSeek Harness — policy-check every tool call before it runs

Security3