dsh-anchored-subagent
Say the secret handshake: DSH subagents start on the Minimal two-tool condition to unlock DeepSeek's full RL-trained strength, then get the whole toolbox.
119 results
Say the secret handshake: DSH subagents start on the Minimal two-tool condition to unlock DeepSeek's full RL-trained strength, then get the whole toolbox.
V0 capability-disclosure scanner for DeepSeek Harness (DSH) cordis plugins: reports which sensitive services (credentials/shell/approval/sandbox/fs/tools...) a plugin declares or references before you trust it.
Secret & dangerous-pattern scanner for DeepSeek Harness — a security_scan tool that finds leaked API keys, tokens, private keys and credential files, with full redaction.
Content-addressed proof for body-free DSH tool-result custody stages
One install for SpecFlow, GitFlow, Guardian, and Code Intel on DeepSeek Harness.
Evidence-first inspection, compatibility verification, and quarantine tooling for DeepSeek Harness plugins.
Agent 专用的 DSH 插件检索、审计、安装与验证工具桥;不提供可视化市场界面。
A DeepSeek Harness Web plugin for inspecting redacted LLM HTTP request and response traces.
DeepSeek Harness 工具调用安全守卫插件:规则引擎拦截 + 路径白名单 + 敏感文件黑名单 + 人工审批 + 审计日志 + 侧边面板
DeepSeek Harness plugin: plants a canary string in model-visible context and denies any tool argument or outbound URL that echoes it back
DSH 危险命令守卫:通过 tools/pre-execute 门禁拦截 bash/pwsh 高危命令(rm -rf /、mkfs、dd 写设备、管道执行脚本、git push --force 等),支持分级策略(极高危始终拒绝 / 中危跟随全局 deny/ask/log)、用户自定义规则与白名单。
Project DeepSeek Harness tool, approval, and result facts into a bounded action lifecycle ledger.
DSH-Plugin: structural observability layer — real tool/skill usage recording (tools/result), skill-catalog audit, and a watchdog with health/error events. No model self-reporting.
Agent governance suite for DeepSeek Harness (enterprise companion): policy-based tool gating (allow/deny/ask), structured JSONL audit trail, and per-agent token quotas against the host token meter — state under $DSH_HOME/gov
Tolerate redundant sandbox_permissions requests: a tool call asking to escalate to a mode that is not strictly wider than the session's standing mode runs as-is at the standing mode instead of failing with "not strictly wider". Genuine escalations still route through the approval flow.
DeepSeek Harness (dsh) plugin adapter for litkit — academic literature search, citation audit, and download tools. Root npm package of the polyglot litkit-search monorepo, so `dsh plugin add github:bpc-oss/litkit-search` installs the adapter directly.
Guard DeepSeek Harness PowerShell, file, image, and search tools on Windows with workspace, credential, approval, and audit policy.
Docker-container (WSL2 backend) shell executor for the DeepSeek Harness bash capability seam on Windows: every bash tool call runs in a disposable Linux container with the workspace bind-mounted.
LaTeX compile check and BibTeX lint/fill/audit tools for DeepSeek Harness and any agent.
Bridges vendor agent SDKs into DeepSeek Harness as selectable LLM providers. Works in any DSH mode; DSH keeps its own prompt, tools, sandbox and approvals.
此为 DSH 生态插件。Dolphin - 主动巡检型安全防御插件,支持本地扫描与远程 SSH 巡逻。将渗透测试方法论(信息收集→漏洞探测→利用验证→报告)转化为主动防御巡检流程:基于 Semgrep 的扫描层与基于 SSH 的执行层相融合,可对本地目录做静态扫描,也可将扫描命令经 SSH 下发至远程主机执行并回收结构化结果。
Workspace tools for DeepSeek Harness: per-workspace default Agent preset and permission preset for new sessions, using only official extension points (no DSH patches required).
`dsh-quick-invoke` 是一个面向 DSH Web 的独立 Cordis 插件,为 Skill、Agent preset 和 Plugin 提供统一的 `/` 快捷入口、候选选择和 Host 命令执行能力。 本插件不修改 DSH 核心,不提供任意 Tool 直调语法。Tool 仍由 Agent 根据自然语言选择,并继续经过 DSH 的 tools、approval、guard 和 permission 流程。
OpenKapsel workspace bridge for the DeepSeek Harness: operate a remote OpenKapsel workspace (files, shell, context, memory, sharing, preview) through skill-driven tool calls using only its workspace URL and control token.