All Plugins

Session lifecycle CLI: export (md/json/jsonl), archive/restore, trash, search, and stats. Read-only by default; nothing is ever deleted by the engine.

Verification-driven self-evolution loop: failure logs become verified AGENTS.md rules; in-session plugin (evolve_learn / evolve_apply / evolve_touch / evolve_recall), tool-verify gate, rule lifecycle, local recall.

The pet that grows with your agent: 5 evolution stages earned from real signals (verified rules, completed sessions, tool calls, compactions), agent-state mirroring, and one-click growth share cards. Zero dependencies, 100% local.

Organize folders and sessions into projects with shared PROJECT.md memory and AGENTS.md instructions injected into every session, plus a project tree sidebar.

On Windows, the available bash tool is limited to Git Bash and PowerShell is disabled.

System-level desktop notifications: turn-completion and workflow-end banners, plus a modal alert when an approval is needed (macOS osascript / Linux notify-send).

Free-interval session reports with AI-narrated daily/weekly digests over any date range, plus every-N-days scheduled reminders with system notifications (macOS / Linux).

Notion connector for DeepSeek Harness: search, read, query, create, update, and append Notion pages and databases via six agent tools, with a Web settings page — configured once with an Integration Token.

Slash-command console for dsh: /web start|stop|restart|status, /tunnel SSH forward management, one-shot /ask, and a console TUI launcher.

Two-tier image reading for text-only models: fast local OCR (RapidOCR, offline) first, vision-model fallback (modlens).

Vendor-based usage dashboard: per-provider token/cache/output KPI, a 53-week heatmap, trend chart with hourly "today" view, model drilldown, cost estimation, CSV export, and health cards (TTFT, generation speed, peak context, error rate).

Matt Pocock's 25 skills fully translated to Chinese (technical terms kept in English with glosses).

Registers a SpecWorkflow skill pack for requirement clarification, implementation specs, execution, delivery review, repair planning, bug diagnosis, and source-backed research.

Give text-only models vision: a describe_image tool that delegates images to a vision model from your dsh model list over the harness's own LLM runtime.

Per-process tool-call statistics: a `tool_stats` tool reporting per-tool call counts, error counts, and average durations.

Skill for packaging DeepSeek Harness into a Tauri 2 desktop app (macOS + Windows): dual-platform install playbook, China mirror bootstrap with a subagent timeout sentinel, admin-free Windows toolchain recipe (no VS Build Tools), and three-path acceptance checklists.

Chrome side panel that embeds the dsh web UI and lets the agent read the current page, capture HTTP traffic, and drive the browser.

Floating cost crystal for the Web UI: balance card, real-time tok/s, peak/off-peak billing countdown, last-24h spend, and a 🔮 next-message cost forecast, all timezone-aware.

Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.

CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.