Plugins

Exposes the Paper-gogo evidence-first paper workflow as native tools: all 18 phases and the seven G0-G6 gates become callable, gate results are normalised and advancement is refused while any gate fails, and claims are audited against the four evidence states SUPPORTED, INFERRED, VERIFY and MISSING. Ships the workflow text and 57 skills in its own directory, so it installs without a separate Paper-gogo package.

Music composition inside the conversation: the model writes a score against a bundled composing skill, and a play_score tool renders it as an inline card with a piano roll, Web Audio playback and WAV/JSON export.

Adds a human-editable notes workspace with folders, full-text search, rich text, checklists, resizable tables, attachments, exports, and opt-in agent collaboration.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Readable transcript export for DeepSeek Harness: turn any Session into a Markdown / HTML / ZIP transcript with reasoning blocks, tool calls and results, images and usage — from the Session header or the /export-md command.

DeepSeek Harness plugin that wraps @stardeckai/lgtm — a Jev-powered linter for tests that pass but prove nothing. Ships the CLI as a dependency, reuses the TypeSafe credential stored in DSH, and exposes lgtm_audit / lgtm_status to the agent.

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.

TypeSafe Jev (modèle de décision System One) pour DeepSeek Harness, de bout en bout : jev_decision (choice/score/noul, parallèle, réponses typées + confiance), une carte Paramètres > Plugins pour la clé API et les bascules, des vues d'outils en ligne montrant chaque décision dans la conversation (réponse, confiance, latence, coût), un garde automatique (contrôles déterministes + risque/boucle Jev), un tableau de bord local /jev, et un benchmark de vérification en ligne (96,3 % sur 27 questions étiquetées, médiane ~283 ms sur jev-latest, 2026-09-21). Honnête par conception : API réelle uniquement, aucun repli simulé.

Bridges Feishu, WeCom, DingTalk, QQ, Slack, Discord, Telegram and Mattermost into dsh agents (outbound WS/Stream/Gateway/long-poll/webhook), with im_status, optional local Whisper ASR, plain-text outbound for QQ/DingTalk/Telegram/Mattermost, and env CSV allowlists (DSH_IM_*_ALLOWED_USER_IDS). Empty allowedUserIds means EVERYONE can drive your agent — set a whitelist before exposing a bot.

Skill usage scoreboard for DSH: counts both per-session deduplicated and per-load usage, scores `skill` tool calls and direct `read` of skill files, and shows the tally in a three-tab settings page (skill ranking, session board, management) with paging and JSON import/export.

Windows desktop control exposed as native DSH tools - whole-screen and single-window capture (the window one goes through PrintWindow, so a covered window still captures), click, drag, typing, keyboard shortcuts, scrolling, window management, pixel and window polling, and UIA queries that can invoke a control or read its value instead of clicking coordinates. 11 tools over a PowerShell 7 child process; no MCP server, no resident process, no API key.

Graft, forward and fork DSH sessions: read a slice of one session log, export it, fork at a turn boundary, or forward a selection into another session as a self-contained graft message.

Unified observability (trace/log/metric) for deepseek-harness plugins: hooks dsh session telemetry where available, maintains OTel signals where not, and exports via standard OTLP.

Auditable token ledger for DeepSeek Harness: folds the durable session log into restart-safe totals, recomputes the same numbers from the raw logs and diffs them, and turns usage into a bill by workspace, session, model or vendor, exportable as CSV or JSON.

Compares existing DSH sessions or runs controlled A/B trials between agent presets, showing aligned timelines, paired metric deltas, explicit success checks, and exportable reports.

Adds a Canvas drawer and eight model tools to create, patch, version, and export HTML, Markdown, Mermaid, SVG, and React artifacts.

Capture selected DSH, local MCP, or native WebMCP calls as reviewed, parameterized routines, expose typed tools, and replay with fresh approval.

DeepSeek Harness (Cordis) plugin — bi-temporal VSA memory + cognition engine + BLAKE3 provenance, exposed as a DSH storage+session plugin. End-to-end tested with a real Python subprocess.

AI 编译纯文本小说工作台 for the dsh web GUI: import a novel outline (docx/text), plan volumes & chapters with LLM, generate chapter by chapter (3000-4000 chars each), auto AI review & book audit, and export the full book as Markdown/TXT into your chosen output fold

Global prompt-injection / context-virus defense for DeepSeek Harness: scans tool arguments, tool results, pre-model messages and the outbound stream; quarantine/block/monitor modes, canary trap, and an evolvable on-disk signature library with learn/import/export.

Renders workspace Markdown files in a standalone full-screen reader with GFM, KaTeX, Mermaid, outline navigation, live file reload, and browser printing/PDF export.

Advises or applies allowlisted Windows portproxy for a WSL listen port, preferring the kit :3081 relay and launch token for local dsh UI.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Safe Git Credential Manager hints for WSL without exposing secrets.