Plugins
Browse, filter, and install DeepSeek-Harness plugins.
93 plugins found
dsh-claw-identity
xingyingyuzhui/dsh-claw-identity
Injects SOUL, IDENTITY, AGENTS, and TOOLS into Claw session prompts. Hard dep (install together or single install fails): dsh-claw-permissions.
dsh-dual-host-plugin
mogragsigma/dsh-dual-host-plugin
Single-owner cloud tasks for DeepSeek Harness (大肥鱼 bot): submit from local chat or either IM bot, run continuously in a native cloud worker, and follow overall progress and artifacts in one workbench. Task permissions are independent of IM; includes agreed delivery and session archive recovery.
dsh-grantwrite-patch
0-v-0/dsh-grantwrite-patch
Windows sandbox ACL-repair plugin for DeepSeek Harness (dsh) — fix the grantWrite failure (SetNamedSecurityInfoW Win32 5) and retry the command invisibly
dsh-multi-folder
helloqingtao/dsh-multi-folder
DeepSeek Harness plugin: secondary working directories for a project. The agent keeps the primary workspace as cwd, gains equal write/exec permissions on configured secondary directories under workspace-write mode, and is notified of configuration changes
dsh-siyuan-archive
yyk0402/dsh-siyuan-archive
Archives DSH conversation output into SiYuan notes: a single siyuan_archive call files content under `<archive path>/<year-month>/<type>/<date>_<time>_<topic>_<content>` with a metadata table and auto-maintains an index document at the notebook root; 6 siyuan_* host tools (list notebooks, full-text search, read document, archive, delete block, remove document) and a Web settings page for base URL with connection test, API token in the host credential store, archive target and title template, plus notebook/document-level read/write/delete permissions with default deny and child levels able to only tighten.
dsh-shell-cmd
xx529/dsh-shell-cmd
/cmd <command> in the composer runs that shell command in the session working directory, sends the command and its output to the model as a user message, and renders the input as a terminal card with exit status, expandable output and copy buttons; a bare /cmd opens an interactive terminal whose transcript is sent to the model with Ctrl+Enter. Runs with its own terminal permissions (danger-full-access) by default; set useSessionPolicy: true to use the session sandbox.
dsh-plugin-guard (dsh-guard-tool)
ryesama/dsh-plugin-guard
Registers one agent tool, plugin_guard, that statically scans a DSH plugin package before it is installed and reports a verdict with the reasons: a missing or broken dsh.bundle.patch, a missing dsh.permissions block, install scripts, dangerous APIs and obfuscation, dependency risk, and source that is not indexed and therefore cannot be verified. Read-only: the scanned code is never imported, installed, evaluated or run.
dsh-dotclaude
rui-debug769/dsh-dotclaude
Runs a Claude Code project's .claude/ slash commands and permissions.deny rules inside DeepSeek Harness. Command bodies expand $ARGUMENTS, positional arguments and @file references into the agent's next turn; matching tool calls are denied before they run. Every host service is probed, so a host without a command registry, working-directory service or TUI status line degrades one feature instead of failing the boot.
dsh-sandbox-noop-escalation
zzstar101/dsh-sandbox-noop-escalation
Removes sandbox_permissions / justification arguments that cannot widen the call's current sandbox mode, so calls no longer fail with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "danger-full-access" mode'. GPT models tend to fill these optional fields on every call and pick workspace-write, which is narrower than danger-full-access. Runs in tools/pre-execute: compares the requested mode with the mode the session's sandbox policy resolves, and drops the fields when the request is the same or narrower (also drops a lone justification). Also understands the values GPT carries over from Codex's own shell tool: null, empty and use_default are treated as no request, and in a danger-full-access session any value (including require_escalated) is dropped because nothing is wider. Real widening requests, unknown modes and tools that do not advertise DSH's escalation schema are left to DSH core. Never widens permissions. Configurable tool list (default bash, pwsh, write, edit, run_code). Zero dependencies.
dsh-auto-handoff
qingyou002/dsh-auto-handoff
DSH plugin: hands a long session over to a fresh session in the same workspace on /handoff or at a token threshold, carrying the preset, model, permissions and plan mode across; the brief is written by the session's own model and the switch waits for a step boundary instead of interrupting running work.
dsh-project-guard
inceptzws/dsh-project-guard
DeepSeek Harness permission guard: work inside the workspace is never interrupted; only the extra permission a call asks for is judged — machine-safe actions pass, system changes ask with a consequence analysis, destructive ones are refused.
dsh-jumpserver
we39/dsh-jumpserver
Query and manage JumpServer through conversation: assets, users, accounts, permissions, sessions, command audit logs, command filters, and RBAC roles, authenticated with an AccessKeyID/AccessKeySecret pair (HTTP Signature).
dsh-sandbox-arg-guard
apex-mochen/dsh-sandbox-arg-guard
Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.
dsh-plugin-sage-subagent
gezi-wen/dsh-plugin-sage-subagent
Named, file-defined subagent roles for DeepSeek Harness: persona, subagent-only skills, tool permissions, an ordered model chain with failover, and derived groups.
dsh-bash-escalation-gate
ruby1304/dsh-bash-escalation-gate
Require a real, immediately preceding sandbox denial before DSH Bash can request wider permissions.
dsh-escalation-advisor
zhangqian98/dsh-escalation-advisor
Three-mode visible-session advisor plugin for DeepSeek Harness with configurable tool permissions, local-subagent coverage, and task-tree budgets.
dsh-sub-cli
dingminhua/dsh-sub-cli
Unified management and invocation of external Agent CLIs in DSH, fully isolated from the user's native installs; preset Provider, model, reasoning effort, and permissions per CLI, callable directly or like native subagents.
oh-my-dsh-slim (npm-package)
ninipa/oh-my-dsh-slim
Specialist subagent delegation preset (orchestrator + 5 roles: oracle/designer/fixer/explorer/librarian) that seeds itself into your DSH home — background-first delegation, JSON-driven models/effort/tool permissions, scoped MCP for research.
capmark
taltara/capmark
Hold a DeepSeek Harness agent to a capmark capability manifest: mask its tools and judge every call.
dsh-settings-tuner
semidia/dsh-settings-tuner
System parameter adjustment UI: grouped settings page for timeouts, parallelism, LLM retry policy, model params, web search, permissions and presets; safe profile-config editing with line-level YAML matching and post-write validation.
dsh-feishu-remote
shixiangyu2/dsh-feishu-remote
Control a DeepSeek Harness agent from Feishu/Lark: send a task by DM, an agent runs it with your configured model and replies in the chat, and a feishu_send tool lets the agent push results. Uses lark-cli's WebSocket connection, so no public webhook is needed, and ships a resident launcher. Note: the plugin does not check who sent a message, so anyone who can DM the bot — by default, members of the Feishu tenant the app belongs to — can drive an agent running with the host's own model credentials and file permissions. Setup is not one `dsh plugin add`: `lark-cli` must be installed and authenticated once, and a Feishu self-built app with the permissions the README lists is required.