Plugins
Browse, filter, and install DeepSeek-Harness plugins.
52 plugins found
dsh-ros2
stvli/dsh-ros2
ROS2 debugging toolset and robot-state vision analysis for DeepSeek Harness: node/topic/service/action/interface/TF enumeration, whole-graph topology JSON, rosdep checks, approval-gated builds and custom message scaffolding, GUI screenshots and multimodal vision observation, plus headless RViz2 offscreen rendering (low-poly meshes, direct pixel read, GPU passthrough - motion rendering at 30Hz) with parallel VLM realtime analysis.
dsh-turn-fold
ch4acko3/dsh-turn-fold
Codex-style turn folding for the DSH Web UI: keeps final answers visible, groups consecutive reasoning and tool activity, and shows configurable live duration, tool-call, and token metrics with multilingual summaries.
dsh-metaphysics
xuanfu-web/dsh-metaphysics
Chinese metaphysics (xuanxue) divination panel and agent tool with nineteen systems: eight chart systems (BaZi, Zi Wei Dou Shu, LiuYao, MeiHua, Da Liu Ren, Qi Men Dun Jia, compatibility charts, Tarot) plus eleven quick references (almanac, solar–lunar conversion, date selection, bone-weight fortune, Xiao Liu Ren, horoscope, numerology, life-curve, feng shui, name analysis, an MBTI-style 16-type questionnaire), with ask-driven, report-style interpretation. BaZi adds exact dayun handover dates, annual suiyun hints, "passing-through" (通关), three-book classical cross-reference, four-mausoleum (杂气) month pattern selection and daily "human element" (人元司权); Zi Wei adds 34 patterns, eleven switchable school variants (including an opt-in full 61-star minor-star table that ships the placement verses alongside the chart), chained flying transformations and three-way-four-corner composite flights; LiuYao adds yongshen strength, whole-hexagram per-line strength, hidden-spirit release conditions and response-time clues (应期), while LiuYao and MeiHua quote the received Zhouyi text in full (64 hexagram statements, 384 line statements plus 用九/用六, cross-checked across three editions with variant readings in brackets); feng shui covers eight-mansion and Xuan Kong flying stars; name analysis ships a 1,062-character library with five-grid (五格) numerology and phonetics checks; tarot ships a card-by-card library for all 78 cards (Rider-Waite-Smith base: English name, card-image description, core meaning and astrological correspondence, cross-checked against three published sources — court cards deliberately carry no zodiac because two published mappings conflict, and the chart says so). A classical-source library now backs the readings: 464 indexed citations from 66 classical works, with 584 verifiable quotations including all 120 Qiongtong Baojian pattern extracts; every quote is checked as a literal substring against a 341-page offline source snapshot, variant readings are kept side by side rather than harmonised, modern editorial notes are kept separate from the classical text, and the quotations with their plain-language glosses live only in a standalone citation index page instead of the browser chunks. Every result can carry a reproducible shadow-chart ID (same normalized inputs → same ID; version bumps auto-diff chart fields) plus optional step-by-step deduction traces (rule, inputs, result and source per layer). The browser client ships as a small first-screen entry plus per-tab engine chunks loaded on demand (first-screen gzip ≈ 90KB), while the offline page stays a single file. The DSH panel and the offline page share the same grouped first screen (ask / read a person / pick a date) with recent-used entries and narrow-width folding; charts open with a plain-language conclusion, one-click copy of an ask-ready prompt and saved birth charts, and an unknown birth hour falls back to a three-pillar chart instead of silently assuming midnight. All computed locally; networking is off by default. The npm package also ships an offline single-file page (命理排盘.html): double-click to open, every tab included, no server and no network needed.
project-blueprint
shuguang1994/project-blueprint
Make any project AI-agent-ready in one command. Adaptive tech stack detection (7 languages × 14 frameworks × 61 components), auto-generates AGENTS.md, docs skeleton, CI/CD, and testing infrastructure. 一句话让任何项目具备 AI 开发能力。
dsh-switchman
mrzturn/dsh-switchman
Sessions and messages (`session`): built to defuse the three ways a long agent session fails. 1) The context window fills up — the session gets dull, forgets earlier agreements, or dies mid-task. The plugin manages the context watermark end to end: automatic folding at idle boundaries with a persisted fold ledger and deterministic rebuild (the serialized prefix stays byte-identical between folds, so the provider prompt-prefix cache keeps hitting), a protected recent tail, three escalating watermark tiers, and an automatic write-handover-doc-then-compact at the top tier that never abandons running subagents — the main session never explodes, and token spend tracks the work instead of the chat length. 2) File edits fail in loops — a missed anchor burns turn after turn. A listener rewrites native `edit` / `str_replace_editor` misses into self-contained corrective feedback: per-match excerpts of the file's exact text, the failure class (whitespace drift, multi-hit, zero-hit…), the correct retry recipe, and a loop-guard that orders a strategy switch after three same-class failures — the model fixes itself on the next try instead of guessing. 3) One model in one burnt-out context loses perspective — advantage-based delegation dispatches across six model pools (economy/mechanical/main/hard/vision/review, optional intent routing) only when it wins: a pristine child context that has not spent a token on your history, an independent model/effort lane, parallelism, blast-radius isolation; detail-bearing edits are still done directly. When two of three structural constraint tags fire in a turn, an Agent Team assembles autonomously; otherwise plain subagent dispatch stays the default, and tiered verification routes larger or core changes to independent reviewers. Also: per-scope output-language preferences, token tracking (no bill calculation), read-only MySQL/Redis checks plus commit-message and requirements-doc skills, and an offline session-log repair tool. Every capability above serves the live session and its messages. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
fold
shaneconner/fold
Lossless context folding for DeepSeek Harness: the oldest span is replaced by a brief, and the originals stay in the session log.
dsh-token-saver
shaw529/dsh-token-saver
DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.
dsh-toolfold
minecraftbe/dsh-toolfold
Codex-style tool call folding, collapsing multiple tool calls into a single line.
dsh-plugins (global-pins)
delthin/dsh-plugins
Aggregate pinned sessions that are currently rendered and visible across workspaces into a single sidebar view, saving you from digging through separate workspaces. The aggregated section can either stay above the workspace list with independent scrolling or scroll inline with the list, directly reusing native session rows, status indicators, and actions while respecting current folding and search filters without forcibly expanding hidden items.
dsh-message-fold
ryensx/dsh-message-fold
Provides Codex-style session message folding for DeepSeek Harness.
dsh-ios-simulator-helper
zhz8888/dsh-ios-simulator-helper
The official ZCode ios-simulator plugin ported to native DSH tools: the original 20 ios_* tools keep their names and arguments, plus ios_shutdown_simulator, covering Xcode project discovery and scaffolding, simulator boot and shutdown, build, install, launch and terminate, screenshots, log reading, an in-app settings page and optional idb UI automation. macOS only.
new-project-init
warm-flame-core/new-project-init
Project documentation scaffolding skill: question-driven setup of project standards, AI-collaboration workflows, and memory discipline across DSH, Reasonix, Claude Code, and Codex.
rcs-context
screamingmaggot/rcs-context
Reversible context folding plus external memory for DeepSeek Harness: tool output collapses into expandable lines, session facts become auditable records.
dsh-token-saver
lovedolove/dsh-token-saver
DeepSeek Harness plugin that trims tool output (head/tail plus grep folding), adds optional prompt shaping (Caveman and Ponytail), instant local responses, RTK command-output compaction, context-pressure handling, optional LLM-summary compaction, stable prompt-cache layout, a Web settings UI, and persisted savings telemetry.
dsh-plugin-maker
goatliamia/dsh-plugin-maker
Plugin development toolkit for DeepSeek Harness with scaffolding, contract checks, plugin vetting, impact analysis, and upstream compatibility tracking.
dsh-live-process
cstcood/dsh-live-process
Drives the official disclosure rows so thinking, tool, command and context-injection rows unfold while they run and fold when they settle; adds elapsed badges to thinking, tool and command rows, a choice between folding on end or on arrival of the next row, per-block overrides, and separate dark and light colour schemes.
dsh-vizro
lion231226/dsh-vizro
Vizro dashboards inside DeepSeek Harness: seven native tools for the model contract, production-path validation, data profiling, scaffolding, preview servers and health checks, six authoring skills, and a workbench panel. No MCP server.
dsh-compaction-manager
rickt34/dsh-compaction-manager
Compaction settings panel: orders model-free compaction steps (official head/tail pruner, Magic Compact-style output omission, DCP-style dedupe and error purge, tool-call folding), tunes compaction-basic, adds a per-session Compaction tab that previews savings and queues a compact-now run, and adds a restore_context tool that returns hidden content.
dsh-plugin-sticky-wall
zmengle/dsh-plugin-sticky-wall
Sidebar sticky-note wall with colour-coded notes, checklists, folding, a trash drawer that restores deleted notes, drag and resize, and five sticky_wall_* model tools for writing and restoring notes from chat.
dsh-plugin-builder
wilshi/dsh-plugin-builder
A settings-tab workshop plus the cordis-plugin-development skill it hands to the agent, for writing DSH plugins against the running host API.
dsh-fold-polish
five0016/dsh-fold-polish
DeepSeek Harness conversation polish: message and step folding, composer and sidebar sizing, folded-content search, turn timing, and confirmed local conversation history deletion.
dsh-chat-settings
fallnstrelitzia/dsh-chat-settings
Per-conversation system prompt, turn-based context folding, sampling overrides and a low-token pure chat mode for DeepSeek Harness.
dsh-ocr-review
jayyuen666/dsh-ocr-review
Wraps the external `ocr` (open-code-review) CLI in seven model tools — review, whole-tree scan, deterministic file selection and rule scaffolding, session history with comment filtering, compare and export, rule diagnostics and read-only LLM catalogue queries — with its own shape, type and enum gates, and reports what OCR found separately from whether the run covered the selected files; its settings card selects a provider/model from the host settings catalogue, edits the CLI `mcp_servers` JSON, reports `ocr auth` status, switches the ChatGPT model and measures the installed CLI version. The external CLI must be installed separately; the plugin never installs or upgrades it.
dsh-rainbow-activity
nzlov/dsh-rainbow-activity
Adds ordered colour strips and step counts to native DSH Web activity summaries without changing messages or folding.