Find the right DSH plugin
for your next workflow

Enables or disables DSH plugins from Settings → Plugins: each toggle stops or starts the plugin immediately without a restart and the change persists across restarts.

Auto-adjust model reasoning effort per task (off/low/high/max): task classification, \[effort=...] markers, in-turn error escalation, DeepSeek peak-pricing-period capping with countdown notices, and manual-selection priority.

One-click start/stop launcher for DSH Web on macOS — start (foreground/daemon), stop, status, duplicate-launch guard, auto browser open, plus a Dock-able DSH.app built by script.

Context injection audit: token costs of instruction chains / skill catalogs / tool schemas, duplicate and conflict detection.

Continual self-evolution: versioned, auditable, rollback-safe harness state (prompts, memory, skills, subagent specs) refined from session trajectories, with review gates and hot-reloaded skills.

Crash protection for installed plugins: crash cards with one-click disable, static pre-flight inspection, black-box crash telemetry, and a safe-mode rescue profile for a broken UI.

China-network bootstrap for dsh: probes npm/npmmirror/GitHub/HuggingFace/Gitee and local proxies, reads registry config, recommends mirrors/proxy, and generates a PowerShell + bash bootstrap script. Read-only by default; apply is explicit. CLI plus an agent-callable cn_boot tool.

Dependency supply-chain hygiene audit for dsh projects and profiles: peer-range resolvability, broken dist-tag detection (#2763 class), stale / missing-license / non-registry dependencies, and installed-vs-declared drift — CLI plus an agent-callable dep_audit tool.

Official GitHub Discussions radar for DeepSeek Harness: list, filter and search the official boards (Ideas / Q&A / Show Your Plugins! / General / Announcements / Polls) — CLI plus an agent-callable discussions_radar tool, dsh-discussions-radar/v1 reports, zero runtime deps, read-only public API.

Disk-usage audit for dsh data directories: total size, per-directory breakdown, largest files, oversized-file warnings (session logs can hit hundreds of MB) and cleanup suggestions — CLI plus an agent-callable disk_audit tool, dsh-disk-audit/v1 reports, zero runtime deps, read-only.

First-run health check for DeepSeek Harness: verifies Node/pnpm/dsh toolchain, home, profile, API key (names only, never values), workspace writability and npm registry, then prints actionable next steps — CLI plus an agent-callable quickstart tool, dsh-firstrun/v1 reports, zero runtime deps.

Generate llms.txt for dsh plugin repositories from package.json + README — AI-readable discovery files, zero runtime deps, read-only by default. CLI plus an agent-callable llms_forge tool.

Health checks for DSH plugins: manifest/patch/entry/build/pack/install verification, model-callable plugin_check, profile host-shadowing + BOM detection, environment diagnostics, and poison preflight.

Plugin quality scorecard for DeepSeek Harness: 0-100 with grade, 6 components, fix suggestions per deduction, batch leaderboard - CLI plus an agent-callable quality_score tool.

Generate README.md for dsh plugin repositories from package.json + cordis.patch.yml + source layout — install/CLI/tools/dev/license sections, deterministic, zero runtime deps, read-only by default. CLI plus an agent-callable readme_forge tool.

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.

Turn-based time tracking from dsh session logs: totals, per-day/project/provider/source rollups, tool-call counts, failure rates, and time-to-first-token — CLI plus an agent-callable timesheet tool, dsh-timesheet/v1 reports, zero runtime deps.

Plug/unplug any DeepSeek Harness plugin cleanly — list every mounted layer (bundles + patch rows), remove with full cleanup, disable/enable without deleting, and audit for orphaned/dangling state. CLI + agent-callable unplug tool. Read-only by default; destructive operations require explicit confirmation.