dsh-linked-folders
Multi-folder workspace: a durable global linked-folders list plus per-session on-the-fly linking (link_folder/unlink_folder), managed from the Web sidebar with a native folder picker.
多文件夹工作区：全局链接文件夹列表 + 会话内临时挂载（link_folder/unlink_folder），侧边栏管理并支持系统选目录。
How to install
dsh plugin add @steven-wu/dsh-linked-folders About
@steven-wu/dsh-linked-folders Out-of-tree dsh plugin that gives a session **multi-folder workspace** access — like Codex's linked folders. A **global linked-folders list** (durable, cross-session) — your "global workspace". **Per-session temporary links** the model adds/removes on the fly with link_folder / unlink_folder. Both lists are injected into the system prompt, so the model knows which extra roots it may cd into and work across. Install The package declares a dsh.bundle manifest, so dsh plugin add installs it and adds it to the profile's bundle layers automatically: sh dsh plugin --pro…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-08-17
- Created
- 2026-08-16
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin, curated:0xsline/awesome-deepseek-harness
- Topics
- deepseek, deepseek-harness, dsh-plugin
Related plugins
dsh-chat-import
Nwflower/dsh-chat-import
Import full-fidelity chat histories from 13 coding agents (Claude Code, Codex, ChatGPT, Cursor, Gemini, opencode, and more) as resumable DeepSeek Harness sessions, with reverse export back to Claude Code.
task-passport
dongsheng123132/task-passport
Carry durable task state across DeepSeek Harness, WorkBuddy, Claude Code and Codex with machine-readable checkpoints and optimistic locking.
dsh-turn-rewind
Anionex/dsh-turn-rewind
Rewind conversation and workspace state, powered by a persistent Change Ledger.
deja-vu
vshulcz/deja-vu
Memory for coding agents. Indexes the sessions 17 agents already wrote to disk, including months from before you installed it, and recalls them in any of them. No LLM, no embeddings — one local Go binary.