dsh-anchored-preset-installer
One-command installer for the dsh-anchored-standard experimental presets (Anchored / Zero-Anchored / Whoami Standard)
362 results
One-command installer for the dsh-anchored-standard experimental presets (Anchored / Zero-Anchored / Whoami Standard)
Complete mobile PWA for DeepSeek Harness (DSH): secure LAN/Tailscale remote access gateway + install-to-homescreen (manifest), offline-capable service worker, touch-first gestures, agent-done notifications, and dark compact mobile UI. 移动端 PWA 完整方案 for DeepSeek Harness.
Control the DeepSeek Harness Web UI left sidebar width (min/max/default) by patching the installed ui-layout client bundle at dsh web startup.
Plugin insight center — one answer to '哪些值得装': requirement matching (plugin_guide), environment recipes (recipe), health scoring (plugin_rank), static security scanning (plugin_audit), and a single install verdict (plugin_verdict)
Black hole theme plugin for the DeepSeek Harness Web UI: WebGL Schwarzschild black hole background with deep-space glass panels, switchable from Settings > General > 主题-黑洞. Install into a web profile: dsh plugin --profile web add <path-to-this-package>
DSH plugin: auto-downscale oversized images (and a portable Agent Skill). Powered by sharp. Install from GitHub — no npm publish.
Manage installed DeepSeek Harness skills: browse the full catalog in Settings (beyond the "/" picker), enable/disable without uninstalling, and delete into a restorable trash. Works on desktop and web.
DeepAtlas provides local capability assurance for DSH: on-demand discovery, provenance-backed recommendations, pinned risk review, and controlled installation. DSH 本地能力保障:按需发现、证据推荐、固定版本审计与受控安装。
Run commands on the Windows host's Git for Windows Bash from DeepSeek Harness. WSL-aware, auto-detects the git-bash install path, zero runtime dependencies.
June dual-persona agents (June-M / June-S) for DeepSeek Harness: a dsh bundle that installs the june-m and june-s agent presets plus the git-backup and june-style skills.
Hot-reload installed DeepSeek Harness plugins without restarting dsh web: watches plugin bundles, reloads changed plugins in place, and restarts on dependency changes
One-click curated plugin starter pack for DeepSeek Harness — install & configure the most useful community plugins in a batch. · DSH 精选插件包:一键批量安装并配置最值得装的社区插件。
Pre-install supply-chain provenance checks for DeepSeek Harness plugins: verify the tarball you're about to install matches the source you read, before any code runs. Never executes the audited package.
Plugin manager for the dsh web GUI: paste a GitHub repo URL, verify it is a dsh plugin (bundle or pure cordis), install, then update / remove / enable / disable across the full lifecycle, with background auto-update.
dsh plugin: generate/edit images via the locally installed OpenAI Codex CLI
Task-to-skill pairing with a laziness ladder and a safe install cellar. Never overpours, never serves untasted. DSH · Claude Code · Codex
🔥 Hot-swap plugin manager for DeepSeek Harness — install, unload, enable, disable plugins without restarting DSH.
dsh Settings → About: runtime version, env, and installed plugin inventory (requires @deepseek-ai/dsh@0.1.1-rc.1)
Theme picker settings section: switch app themes and manage installed theme plugins through the dsh-market API.
Manage DeepSeek Harness plugins from the web GUI and CLI: install, enable/disable, uninstall — no manual config-file editing. Writes your profile's cordis.patch.yml for you and applies changes live through HMR.
DSH lightweight optimization plugin collection, maintained in one workspace and installed as one bundle.
Wishes that outlive the session — turn a DeepSeek Harness agent's runtime plugins into permanently installed ones, with no pnpm, no network, and no build authorization.
插件管理:设置 → 插件管理(管理插件 / 下载插件 / 开发插件 / 插件包)。M1 持久管理 loader 树插件:原生插件禁用/启用,用户插件禁用/启用/卸载,操作写 profile 配置、重启后生效。
DSH package manager plugin: install dsh-bundle plugins as profile dependencies and hot mount/unmount their bundle patch rows through the official watchUserPatches cordis.patch.yml reload path — no restart, no workspace/.venv second pipeline.