Plugins

A Desktop 0.2.2-rc.1 adaptation of DSH WebTokens that registers a signed-in Chrome DeepSeek web session as the deepseek-web model in DeepSeek Harness, with tool-call transport, reply validation, a Chrome bridge extension, plus install and rollback scripts. It cannot be installed with the one-line plugin add shown on this page: it needs its own installer (node scripts/install-desktop.mjs, which backs up the whole profile first). Prompts, project content and tool results are sent to the DeepSeek website through your Chrome session; the author has tested it on macOS only.

Writes a novel from one idea to a validated manuscript with a code-driven workflow: a JavaScript state machine runs the stages (constitution, outline, design, writing, validation, batch, export) and a 15-step per-chapter loop, PowerShell scripts validate each gate, and versioned checkpoints let a restart resume at the exact chapter. Nine subagent roles do the drafting and review. Needs PowerShell 7 (pwsh) and Python 3.7+; without pwsh the gates record a DEGRADED verdict and the run pauses.

Experiment-orchestration SOP skill for long-running experiments. A top-level model drafts a decomposition plan — subtasks, the model for each, an acceptance figure with tolerance, and dependency order — and dispatches only after the user confirms that plan; each subtask then goes to a lightweight executor subagent as a self-contained prompt, and its report is confined to measured facts and the delta from the agreed figure, with judgement and decisions staying at the top level. Ships one plan template and five task templates (gather, execute, consistency check, read-only review, mechanical transform), acceptance gates split into a task layer and an experiment layer, and three rules that stop internal-consistency evidence from being presented as independent or external validation.

A document generation plugin for DeepSeek Harness: JSON is the core output, structurally managing document content; unifies parameter definition and inheritance, material extraction, validation checking, and scoring across document generation, keeping output on-target, fast, and token-efficient; ships a built-in COSMIC scenario pack as a worked example plus a built-in guide for authoring new scenario packs.

Moves DSH sessions between workspaces with validation of live/subagent/offline states and automatic backups of every move under ~/.dsh/session-move-backups/.

Per-package automatic updates for the DeepSeek Harness plugins you choose. On a schedule it asks npm for the latest version of installed plugins, updates only the packages you check, and skips local link or file installs, pinned versions and packages with errors; upgrades stay inside the major version and skip prereleases by default. Updates go through the profile's own plugin manager, so the profile write lock, pnpm step, bundle-patch validation and hot reload are the host's, and a failed install puts the previous version back. Each cycle is appended to a JSON log.

DSH 自动审查返回格式兼容插件：严格校验 JSON、有限重试，保留合法拒绝。 / DSH auto-review response format compatibility plugin: strict JSON validation, bounded retries, and preservation of valid denials.

DSH plugin: 29 deterministic, offline tools for JSON validation with exact line/column, JSONPath queries, YAML/CSV conversion, text diff, regex capture, encodings, hashes, Unicode, CIDR, JWT structure and timestamps. Every call returns a { result, meta }

Registers one `doc_ocr_sign_fix` tool for DeepSeek Harness: on macOS it diagnoses and repairs the condition where the bundled Python cannot load native extensions (onnxruntime, cv2, pypdfium2) because of the hardened runtime and library validation, by injecting the disable-library-validation entitlement and re-signing the interpreter, then verifying the imports. Operations are idempotent and the original binary is backed up first. It never touches the enclosing application bundle.

Outbound route pool for DeepSeek Harness. Ships 15 seed routes plus a 20-entry candidate pool covering 7 target kinds (GitHub raw/codeload/main, npm registry, PyPI index, HuggingFace, general). Routes are verified before use: upstream IP lists go through a TLS handshake with full certificate-chain validation (a bare TCP check can be answered locally and report dead IPs as healthy), and failures advance a cooldown ladder of 2/5/15 minutes with the fastest healthy route picked per target kind. Routes are applied by rewriting the URL with one of four rules (prefix, registry, index, host-replace), reaching git, pip, npm, pnpm, gh, curl and wget through three paths: the shell seam (download commands the model runs through the bash tool are intercepted and rewritten automatically; commands wrapped by the pwsh tool, and fetches made by the host itself or the renderer, are not covered), two registered tools the model can call directly (line_pool_status, line_pool_run), and child-process spawn. Multi-line commands keep their line breaks and only the download segment is touched. URLs carrying credentials (user:token@host) are never rewritten, so tokens are not forwarded to third-party mirrors. No global config is modified. A sidebar panel lists every route with latency, failure reason and cooldown countdown, supports per-route retest and enable/disable, and shows live TUN/proxy status from network-adapter and loopback port checks. The candidate pool is re-verified every 24 hours so newly usable routes are added and dead ones dropped. 570 tests, 87% line coverage.

Adds two visual pages to DSH Settings. MCP servers are kept as a JSON source of truth that rewrites the profile patch managed block, with YAML validation and timestamped backups, plus import of a pasted mcpServers JSON that first lists what will be added or overwritten. Thinking unlock probes each OpenAI-compatible gateway for the reasoning efforts it really declares and writes the per-level config back while leaving other hand-written YAML byte ranges untouched; the available model list syncs from a separate button that previews additions and removals, then writes levels and models in one atomic pass, and can also run on the page schedule.

Registers the project-cross-migration skill for DSH: five-layer agent project migration (conversations, memory, persona, tools, environment) with entry validation, JSONL integrity checks and readable restore. 1,418-message real migration verified across three platforms; pure Python stdlib, MIT.

Standalone DSH plugin for PPT authoring, template selection, validation and editable PPTX export

Runtime security guard for DSH: loader import confinement, HTTP Host header validation, and source patch for VM sandbox escapes (4 CVEs). AI-assisted.

Preset workflow template library: 12 reusable orchestration script templates with wf_template_list / wf_template_search / wf_template_run / wf_template_validate tools and static template validation.

Control panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM validation, GPU detection, and tok/s benchmarks.

The small deterministic operations an agent needs mid-task. JSON/YAML round-trip, JSON Schema validation, text diff, JWT decode, regex testing, SQL dialect transpiling, QR codes, timezone and unit conversion, page screenshots.

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.

Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.

Evidence-backed Skill self-evolution for DeepSeek Harness: redacted trajectory learning, quarantined proposals, arena validation, canary monitoring, automatic rollback.

Verification toolkit for DSH agents: evidence-based claim checking against workspace files with line citations, config validation (JSON/YAML), and read-only URL/npm/GitHub submission-readiness probes.

Education toolkit for DSH agents: lesson-plan skeletons by grade band, quiz scaffolding and answer-key validation, analytic rubrics, Anki/markdown flashcards, and readability levels.