Plugins

Feynman learning-mode plugin: teach → teach-back → judge → re-explain loop rendered as rich HTML lesson cards (mermaid diagrams + shiki code highlighting).

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

Content-addressed artifact, fact, action and report lineage for DeepSeek Harness

Generate self-contained interactive HTML reports from Markdown, tables, charts, China province maps, flowcharts, math, and drill-down tables — a DeepSeek Harness (dsh) plugin

运行在 deepseek harness 上的女仆酱

provider-agnostic AIGC HTTP 桥 + 无限画布 + ffmpeg 后处理，13 个工具含画布连边/reroll/媒体编辑 | Provider-agnostic AIGC HTTP bridge + infinite canvas + ffmpeg post-processing; 13 tools incl. canvas linking/reroll/media-edit

DSH port of TaskPlane: dependency-ordered waves run in parallel git-worktree lanes, with task packets, cross-model review, and crash recovery.

Superpowers (obra/superpowers) for DeepSeek Harness: the software-development methodology skills plus their session bootstrap, as a dsh plugin

中文文本人味化 bundle 插件：强制深层改写工作流（十维叙事审计 + 功能路径 + 15 层分布）+ 内容忠实守卫。编辑辅助，非 AI 检测器。

Shows DeepSeek balance and estimated daily spend, merges external vision-call JSONL records, and adds a per-session dashboard with model statistics, TTFT, cache rate, call logs, cost estimates, filters, and CSV export.

DSH balance and quota card showing up to 3 recently used providers. Supports DeepSeek, Moonshot, Kimi For Coding, OpenAI Codex, and OpenCode Go, with auto-discovery, quota windows, reset times, color-coded status, dragging, and automatic refresh.

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

Appends local hash-chained JSONL receipts for tool results and session events without storing prompts, tool arguments, result text, or raw session IDs.

Session execution analytics: steps, tool calls, failures, repeated actions, token usage and verification signals, rendered as text/Markdown/JSON reports.

Compile SVG paths and keyframe specs into self-contained Lottie JSON animation files.

JSON Schema validation: validate/paths/explain/normalize.

Test/extract/safe-replace/statically explain regexes without executing code.

HeartFlow (心虫) AGI layer-1 discriminator gate as a DSH plugin: 47-dimension rule-based text checking (heartflow_check tool) plus automatic output supervision at tools/post-execute, fail-closed when engine missing.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with automatic turn-end persistence and per-agent namespace isolation.

Desktop pet for the DSH Web UI: sprite-sheet animation, agent state linkage, drag, alarm (daily/one-shot) and pomodoro widgets, skin picker with preview.

Host-level proactive wake-ups for DeepSeek Harness: let the model schedule its own alarms (once / interval / cron with random jitter), wake cold sessions on time, gate model-initiated follow-ups with quiet hours and a daily budget, and reclaim silent wake

Ultra-lean daily coding agent preset for DeepSeek Harness (dsh) that strips heavy orchestration for fast, direct tool execution.