Plugins

Local-first memory plugin for DeepSeek Harness: layered L1/L2/L3 memory with automatic capture, manual memos_* retrieval tools, and a built-in memory viewer.

Injects a small continuity pointer at the start of a new session, naming the previous session and any handoff file, and reuses DSH's own compaction summary when there is no handoff file.

Cut token cost in 4 layers without cutting model intelligence: handoff, rtk, headroom, caveman token-saving skills — each also available as a standalone installable plugin.

人脑式上下文压缩逻辑，大幅减少长任务上下文占用以及token消耗

Incremental file mounting with read dedupe: mounted line ranges are never re-sent to the model, on-disk changes invalidate and remount, with a Mounted Files tab and token-savings accounting.

One plugin brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs that rewriting cannot reach are compressed too; common commands such as git, cargo, npm, pytest and docker are covered (rtk itself supports 100+ commands). After compression the model is told what was elided and how to recover it — when the sandbox cannot reach the rtk store, the original is saved separately and its path is given — and `/rtk stats` shows how much was saved. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the command rtk returns would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.

Java efficient development plugin for DeepSeek Harness providing deterministic auto-fix for .java files, token-saving template intents, and cross-platform JDK/Gradle/Android SDK/FFmpeg/LWJGL/IDEA discovery with persistent caching.

Ponytail port: a DeepSeek Harness agent preset that makes the model finish tasks with the least tokens, with lite / full / ultra levels.

Keeps bulk output out of the conversation: ctk_execute, ctk_execute_file and ctk_batch_execute run code in a child process and return only the conclusion, ctk_index and ctk_search file long material into a local FTS5 knowledge base built on node:sqlite, and a routing gate refuses curl and wget before they execute. Ships ctk_stats and ctk_doctor plus a settings page with a live context-occupancy panel. No third-party runtime dependencies.

Converts Office and PDF files in the DSH workspace to Markdown locally — no network, no API quota — before the model reads them. Writes each .md next to its source so only a file path enters the context, and returns byte size, line count, token estimate and a heading outline, for a single file or a whole directory.

Token-efficient web reading for DeepSeek Harness: one call fetches several pages through a real Chrome/Edge over CDP, gates them by relevance and returns a single digest, cutting context tokens by 80-98%. Real search URLs, login flow, screenshots, three proxy modes.

Slims oversized MCP tool JSON Schemas per agent without changing dispatch, and reports token usage, cache hits and context composition on a settings page.

Adds a button beside the composer and a global hotkey palette (default mod+shift+k) that hand one-off questions to a web chat instead of into the harness context: the draft is lifted out of the composer, copied to the clipboard and opened in the templated URL. Ships target-site presets (DeepSeek, Kimi, Qwen, 豆包, 腾讯元宝, GLM, Gemini), a local question history that can be re-opened, copied, or inserted back into the composer, and a settings tab for site, URL template, hotkey, clipboard and history.