Plugins

Adversarial code review — parallel finders inspect a diff through separate lenses (correctness, lifecycle, contract, security), then each finding goes to independent verifiers tasked with refuting it, and one refutation drops it.

Injects allowlisted GitHub Actions and GitLab CI run metadata into agent context without reading logs, credentials, or provider APIs.

GitHub workbench MCP server (dsh bundle): 23 MCP tools for repos, issues, PRs, code review, and search, with zero runtime dependencies and PAT/OAuth auth.

Adversarial multi-lens code review: parallel correctness/security/maintainability lenses attack a diff, with deterministic severity grading, suppression rules and incremental review history.

Git and GitHub panel for the DSH web profile: stage/unstage/discard/diff, branches, commit, push/pull/sync, log, file browser, workflow board, and GitHub OAuth with PR creation.

Policy-driven Git sync for DSH settings and profile configuration, with secret-aware projections, conflict review, and per-line apply controls.

Event-sourced cross-session work ledger: register, track and settle tasks with full audit history, kanban export, and a board digest injected into every model turn.

Disk-persisted execution planning for DSH: milestone/step state machines, dependency gating, an audit event stream, and a deterministic completion gate via dsh tools, CLI, or skill.

Main-brain orchestration preset: delegation-first persona, root-session execution gate, and portable AI-LAW rule skill.

Declarative task-DAG orchestration for DSH: validates dependency graphs, runs topological task layers in parallel through workflow-backed subagents, and propagates failures deterministically.

Workflow tools for the local aflare binary: generate, validate and run local-first deterministic YAML workflow DAGs (WAL crash recovery, Saga compensation) through the local aflare binary, with 300+ templates built in.

Document workshop skill pack: four pure-prompt Agent Skills that turn a codebase into READMEs, PR descriptions, changelogs and code reviews, installed into dsh via a dsh.bundle plugin row.

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.

DSH project scaffold preset: strict 5-phase init runbook, engineering standards and six runnable starter templates (node-ts / react-vite / python / go / spring-boot / monorepo).

Beginner starter pack for DeepSeek Harness: welcome flow, 0→1 learning path, scenario-based plugin recommendations and a self-check checklist, paired with the dsh-handbook-zh Chinese tutorial repo.

Publish an HTML document as a shareable link that opens in one tap and previews as a card in chat apps; publish, update, and export to PNG/PDF/Word.

Real-time duplex voice over Volcengine streaming ASR/TTS: agent reply narration, barge-in, wake word, live captions, 30 Chinese voices and a reply-first acknowledgment; builds in the DSH monorepo.

Voice input for the web UI: a mic button in the composer that transcribes speech into the draft via the Web Speech API, with an optional auto-send toggle.

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.

Lets a text-only DeepSeek agent read images in the same session by delegating to a vision-capable subagent, with send-time image-to-path conversion.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a locally running Unsloth Desktop (Unsloth Studio) server through unsloth_run and unsloth_vision tools; pure HTTP client, never spawns or owns processes.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle management.

Local OCR for attached images via the built-in Windows engine (Windows.Media.Ocr): only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Local OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.