Skip to content
dsh.fish

Browse

33 results

Bundle

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 / MCP 工具的 token 成本,检测重复与冲突;原生 Context Doctor 面板 + context_audit 工具。

Zhenyu9829
Bundle

dsh-chatgpt-bridge

MCP bridge: lets ChatGPT Web create, view, continue and control DeepSeek Harness (DSH) agent sessions through the official MCP protocol. The bridge only connects; DSH keeps its session, agent, tool, approval and workspace security model.

jiezeng2004-design14
Bundle

@tianbuyu-wwx/dsh-hermes-link

Bidirectional bridge between Hermes Agent and DeepSeek Harness. Hermes dispatches focused tasks via JSON-RPC over POST /mcp/collab (one-shot or continuable, nonce-bound amend, secret-bound consult reply); DSH lets you continue Hermes sessions as native DS

Tianbuyu-wwx75
Bundle

dsh-sprites-plugin

Sprites remote development environments for DeepSeek Harness through Cordis and MCP.

superfly6
Bundle

dsh-correctover

Correctover runtime security for DeepSeek Harness (DSH): CCS 7-dimension verification, command-injection/SSRF/credential-exfil blocking, Ed25519 receipts, audit-first. Install with `dsh plugin add dsh-correctover`.

Correctover45
Bundle

dsh-capability-receipt

Content-addressed receipts for skills actually loaded by DeepSeek Harness

dongsheng1231323
Bundle

dsh-capability-toggle-plugin

DSH WebUI capability controls for skills, MCP servers, tools, prompt injections, approvals, and safety guards at session, project, and global levels.

lifeopsgo3
Bundle

dsh-statecore

Native memory for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore

yul7612
Bundle

dsh-policy-drift-proof

Content-addressed, value-redacted policy drift evidence for DeepSeek Harness

dongsheng1231322
Bundle

dsh-audit-bundle

Content-addressed audit indexes across independent DeepSeek Harness evidence producers

dongsheng1231322
Bundle

dsh-pentest-bugtrace

BugTraceAI penetration-testing mode for deepseek-harness (dsh): pentester persona, bundled runbook skill, and the BugTraceAI MCP bridge in one installable profile bundle.

elliseang0000-lang1
Bundle

dsh-ccs-security

Runtime security guard for DeepSeek Harness (DSH) — blocks command injection, SSRF, credential exfiltration, and destructive operations at runtime.

DSHCorrectover1
Bundle

dsh-bailinghub

Let a local DeepSeek Harness Agent use BailingHub to query data, update records, and run permitted actions in your online store, SaaS, or other admin system.

bailinghub1
Bundle

mcp-cap

What can this MCP server actually do? Inspect its real capability surface, seal it, and get told when it changes. Never invokes a tool; gives the server a minimal environment.

liyixuan2012111
Bundle

dsh-skillx

A safe external-skill discovery and adoption bundle for DeepSeek Harness

drowned-fish11
Bundle

dsh-skillnotary

Lock, verify and govern AI agent skills: a DSH plugin that makes the agent check what a skill can do before installing or updating it, and notice when it changes.

liyixuan2012111
Bundle

dsh-mcpguard

Mingleng mcpguard for DeepSeek Harness 鈥?the first security plugin for DSH. Scans skills and MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell and credential leaks.

ChenLaoshiYF1
Bundle

dsh-wolfram

DeepSeek Harness bundle for the official Wolfram/AgentTools MCP server: kernel discovery, a transparent stdio supervisor that owns only its own Wolfram process tree, and a native DSH permission policy over the Wolfram tools.

Zhen-WushuiLingchun1
Bundle

dsh-mcp-security

Fail-closed MCP tool baseline and runtime approval security for DeepSeek Harness.

z-y-q1
Bundle

@xiaoke8698/dsh-memory-forget

Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.

XIAOke8698
Bundle

correctover

AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.

Guigui Wang
Bundle

dsh-harness-os

Agent harness 配置系统:agents/skills/hooks/rules 四层分工、instincts 持续学习(自动学模式、聚簇成技能)、AgentShield 安全审计(secrets/权限/hook 注入/MCP 风险)、Unified Memory Vault 跨 harness 共享、GateGuard 破坏性命令门卫。受 affaan-m/ECC(185k★ MIT)启发。

satan9394