Plugins

Claim-verification skill that checks design documents and plans against codebase facts, escalating behavioral claims to executable logic-primitive verification for state machines and data models, with before/after regression, domain constraints, and concurrency risk mining.

Points web_search at a self-hosted SearXNG instance instead of the native route: pages until maxResults is satisfied, and reports degraded coverage when engines fail so a thin result set is not read as a thin web.

A guarded local fetch provider for the ctx.web seam — the backend dsh does not ship for its own web_fetch tool. Every redirect hop is re-resolved and checked against the non-routable ranges, with a streamed size cap and a content-type allowlist.

Progressive tool disclosure: a deferred tool group costs one catalog line instead of its full schemas until the model loads it with tool_search, with one switch per group in Settings and each group measured against the live registry.

An Obsidian-style knowledge base: ingest sources, let the LLM build and maintain an interlinked wiki, and ask questions grounded in it.

Per provider/model generation concurrency, with a settings card: a cap on how many sessions may stream at once, enforced at the stream and again at subagent spawn, where a fan-out past the cap waits in a FIFO queue instead of failing.

Android companion bridge: QR-code LAN pairing with revocable device tokens and TLS fingerprints, a phone-connection and device-management panel, and an HTTPS access proxy serving sessions, live events and approvals to the paired native app.

Multi-lens structural analysis skill: adversarial-first analysis across 16 lenses in 4 categories with 10 structural tools, confidence calibration, and fact-bound layered output.

Version management for dsh: inspect the installed version against every npm channel or version line, install or downgrade in one click, stream the install log live (rollback-snapshot copy progress, npm extraction progress, elapsed time), roll back instantly from local snapshots, and automate the cycle with a policy engine (silent auto-update, execution windows, daily checks). Never stops npm mid-install — a wedged run is only stopped after an hour, and a half-committed global tree is detected and repaired from the pre-install snapshot automatically. Confirms before installing a found update, auto-restarts the host after install, and falls back to a mirror when the primary registry is unreachable.

Local-first usage and cost meter for the DSH web UI: composer button with live session cost and balance; panel with a stacked per-model daily/7-day chart priced per effective list-price interval (official pricing page synced daily), monthly usage tiers with a canvas share card, 30/50/85% context-pressure warnings with one-click /compact, budget alerts, and an in-panel npm update check with one-click update.

Fine-grained LLM verification for DSH agents: pairwise rewards over score-token logprobs, Probabilistic Pivot Tournament best-of-N selection, and per-step progress tracking.

Static security scanner for DSH plugins: read-only audit (exec, credentials, exfiltration, obfuscation, install scripts, bundle manifest) with a 0-100 risk score.

Custom background image for the DSH Web UI: upload a picture or paste an image URL behind the whole app surface, with opacity, theme-aware scrim, panel transparency, frosted-glass and wallpaper blur, live preview and persisted settings, plus an optional DeepSeek-style timeline rail with per-question bookmarks for long conversations.

DSH updater + official docs sync in Settings: one-click npm update of @deepseek-ai/dsh with live progress (npm output stream, elapsed timer, monotonic bar), multi-copy protection that only touches the running instance, source-tree mode via git pull, one-click PowerShell 7 install on Windows, incremental sync of the official docs/ with progress, and the dsh_docs_search / dsh_docs_read model tools.

Exact-profile control of your real logged-in Chrome browser: an MCP server plus MV3 extension and authenticated localhost bridge for tabs, locators, file injection, media export, and durable scroll capture, with no debug profile or remote-debugging port.

Cost dashboard for DeepSeek Harness: aggregates model input/output/cache tokens across all local sessions, prices them with a builtin table (including DeepSeek peak/off-peak), and shows daily trends plus per-model and per-session tables.

Web GUI bundle for DSH: a task board with cron scheduling, a Git branch graph, a file and change side panel, an SSH terminal with SFTP and port forwarding, QR-paired mobile remote control, a desktop companion, live token statistics, and five installable themes.

UI enhancement suite for DeepSeek Harness: one-click workspace open (copy path, reveal in Finder, open in an auto-discovered editor), DeepSeek-web-style user-message nav rail, session to-do marks, flat-list polish, and a hard-restart button.

OAuth / subscription-plan LLM login (Grok, GitHub Copilot, OpenAI Codex, Anthropic, OpenRouter): durable credential store with on-request token refresh, no repo patches (Grok/Copilot verified; use Codex with caution).

A super-simplified LLM-wiki memory plugin: one index document (auto-loaded) + one markdown file per topic (read only when needed) — no dumping everything into the context and burning tokens. Simple and lightweight, painless to install/uninstall, and freely editable however you like.

Auto-injects user-chosen skills into DSH sessions, either every prompt or once at session start, with a settings page and a composer indicator.

Bottom-right quota pill and panel aggregating membership quotas across AI platforms (Kimi Code, DeepSeek, Zhipu Coding Plan, BigModel, Qwen, Scnet, TokenRouter, SupaWriter), auto-syncing API keys from the DSH credentials domain with colored usage bars.

Web Audio lifecycle cues for DeepSeek Harness: ten configurable events, three low-noise defaults, per-event custom sounds, and no shipped audio assets.

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model