Plugins

Scientific figures as code: agents create a versioned figure IR, patch it incrementally (one node at a time — untouched objects never move), and export publication-ready, true-vector SVG / PDF / PPTX. Seven papercanvas_* tools (create, get, patch, layout, lint, render, inspect) over a deterministic engine with FC001-FC008 quality lint and CJK-aware font resolution. Verified on DSH 0.1.5-rc.3 through 0.2.2-alpha.2. By the author of dsh-sessionflow. Requires the PaperCanvas engine installed separately: Python 3.11+ and the papercanvas CLI (not yet on PyPI — install it from this repository, put it on PATH or set papercanvasBin); the plugin is a thin adapter and ships no engine.

Chinese writing-register plugin for the Gcores/机核 editor 白广大: registers a 40 KB style skill plus style_lint / style_audit / style_rules tools — 4 hard-error and 27 warning checks (banned connectives, slogan inflation, empty quantifiers, uniform paragraphs, unsourced statistics, AI clichés), with thresholds calibrated on 444 articles / 802k characters; a settings page adds an on/off switch, single and batch trial runs, and JSON threshold overrides.

Project-scoped SQLite memory with progressive retrieval, bounded context, a composer button and visual review. Install the repository-root DSH bundle, then run /learning-init with an absolute project path using local Python 3.10+.

Local-first knowledge base for DeepSeek Harness: each base is a folder of UTF-8 text, text PDFs and OCR-read images; the plugin retrieves from the session's selected bases before every turn with Chinese n-gram and BM25, answers carry citations that open in a right-sidebar reader, and the agent gets five kb_* tools (list, search, read, stats, propose text) plus /kb commands for create, use, files, search and rescan.

Adds header buttons that move a started session into another workspace and switch the Agent preset of a session that already began.

Adds a mood system to DeepSeek Harness — 33 named moods judged every 3-6 hours with small per-message adjustments, plus cross-session memory, an aesthetic taste library and an encrypted diary. The mood, memory, taste and diary tools are all callable by the model, and each of the five modules has its own switch. The diary is written only by the model; no summary template is generated. A trimmed fork of JMX-4869/dsh-mood; install either this or upstream dsh-mood, not both, because both register the same mood/diary/taste/memory tool names.

Starpost (星邮) is a social network built for AI bots: one account per bot, with friends, group chats, posts and comments, a public square, message bottles and scheduled Werewolf games, plus daily chat quotas and an anti-repetition limiter. This package is the DeepSeek Harness client for Starpost — 17 tools covering the above, incoming events batched into one prompt at a configurable interval (default 20s) so the agent answers in one turn, and replies sent back out through the same tools. Needs a Starpost account; register one from the plugin panel on first run. A DSH port of the MIT-licensed cortico-world-starpost world extension by hth768 (vendored under vendor/); it cannot be installed alongside that upstream Coo extension.

OpenCode usage dashboard: a sidebar panel for quota and usage in DeepSeek Harness, with Go subscription windows, Console spend, trends, forecasts and model breakdown, multiple accounts, service-account filtering and English/Chinese UI.

Registers Mol* file viewers with dsh-better-sidebar for PDB, mmCIF, MRC maps, small molecules and Chimera .cmm markers, including .gz, with a BioViewer workspace tab and bio_open / bio_add tools.

Reading workbench for DSH: a cover-grid bookshelf and a paginated single/double-page reader for Markdown, TXT, HTML, EPUB, MOBI and PDF, with highlight notes anchored to text offsets and three agent tools for listing books, reading highlights and pulling text excerpts.

Connects QQ private chats and groups to DSH over OneBot 11, adding qq_send and other tools so the agent can reply, send stickers and wait for follow-ups.

Decision 3.0 multimodal decision models for DeepSeek Harness: calibrated-probability tools, a Settings page and a probability-bar card

Native DeepSeek Harness tools for the Kimi browser extension (WebBridge) and KimiCU desktop control: kimi_browser_* drives the user's real logged-in browser, kimi_cu_* observes and operates Windows desktops.

Uncle Sam — answers through chat.deepseek.com in a real browser tab instead of the metered API. Switch between the API and the web account from the composer; web replies are signed so you always know which route answered.

Durable task-decomposition plans for DeepSeek Harness with a self-learning loop: every department subtask runs in three ordered phases (plan, execute, verify), the verify phase must submit a retrospective of problems, detours and resolutions, and that retrospective is written to a permanent lessons file, ranked against the new subtask and injected into later dispatches so the same mistake is not repeated. Adds a read-only dsh_workplan_lessons tool (11 model tools in total), a progress panel drawn as a ring, a stacked bar and per-stage steps, and a public ISO/IEC 15408:2026 security self-assessment with zero runtime dependencies.

Five tools for agent-driven audio: anyaudio_music renders note-level scores offline from local SoundFont banks, anyaudio_sfx offers 52 SoundFont presets plus 15 procedural generators, anyaudio_tts speaks through Edge or MiMo, anyaudio_mix ducks narration under the bed and normalizes peak level, and anyaudio_sources manages the shared sound-font library.

Static-context audit for a DSH home: a six-layer baseline (rules, memory, skills, tool surface, sessions, KB), broken-path checks for a markdown capability map, memory duplicate/stale/over-limit reports, SKILL.md description compression, and tool-surface plus cold-start static-context estimates recovered from session logs. Four read-only DSH tools; writes require --apply and are backed up first. Requires Python 3.10+ on the host (stdlib only; all four tools shell out to the bundled CLI).

Read, message and live-follow local DeepSeek Harness sessions from inside an agent: four tools (session_list, session_read, session_send, session_chat) plus a matching Python CLI, over the desktop app local RPC; transcripts also read offline. Requires Python 3.10+; offline transcript reads also need the zstd CLI.

Give your DeepSeek Harness agent an addressable visual memory: revisit any image, inspect any region, and read exact pixels.

Progressive disclosure agent preset and call directory tool that starts from a minimal baseline and unlocks tools, skills, and MCP servers on demand.

DeepSeek Harness skill bundle for Hearts of Iron IV 1.19.3 modding: scaffold a mod, focus trees, events, decisions, ideas, characters, technologies, MIO, special projects, GUI, localisation, DDS, static verifier, installer and error.log triage. Bundled Python tools; no game assets.

Project-level MCP servers loaded automatically: a project declares them in `.agents/mcp.json` (path and root markers configurable), and every session working inside that project mounts them in its own scope — stdio and Streamable HTTP, tools named `mcp__<server>__<tool>` — with the connections closed when the session ends. A Web UI panel lists the session's servers and their tools, and can enable or disable a project entry after confirmation, backing up and atomically rewriting the manifest.

Auditable mathematical proving for DeepSeek Harness: a local stdio MCP server with 23 machine-checking tools, a bundled workflow skill, and the /prove and /audit-proof commands. proven, refuted and inconclusive are never conflated, and unproven steps are reported instead of hidden. Needs Python 3.10+ with pip install -r requirements.txt on first run; the 23 tools are unavailable until then.

Adds handoff, context-decision and context-diagnose skills, self-contained context_pressure/context_history tools (peak tokens, compaction stats), per-route realWindows with windowSource evidence, routeKey, handoffAt forced-handoff line, and slash commands.