Plugins

Pack a directory into a deterministic tar, read an archive's contents without extracting it, unpack while refusing every member that could reach outside the destination, and verify what came out against what went in by SHA-256. No external dependency — the tar format is written and read in this plugin. Extraction is deliberately more permissive on reading than on writing, because a reader's job is to report what an archive says, while a writer must never emit what it cannot read back. A tar has no central index, so the walk tracks whether it reached the end-of-archive marker: without that, a half-file checksums fine and reads as complete.

Per-turn development progress memory: completed turns are classified into date-indexed Markdown files under doc/progress/ with a maintained INDEX.md, system-level bugs are kept in a cross-project SYSTEM_MEMORY.md and re-injected on error keywords, and a progress_read tool loads full documents on demand.

Bounded self-managed long-term memory (Hermes-style MEMORY.md / USER.md with hard character limits and a safety scan), a review that runs after every turn and writes plain-language notes or refines an existing skill instead of adding a near-duplicate, a curator that finds and surgically repairs skills the loader would silently discard, cross-session search over past messages, and a learning card above the composer that appears only when there is news and asks before it deletes or rewords a memory.

Connects dsh to the GreatArrow.ai MCP server over Streamable HTTP, so the agent can search and save workspace memories, tasks and decisions shared with your other AI clients; a config-only bundle that reads the token from great-arrow.token in the dsh home, never from the environment.

Per-model input type and thinking level declarations on the 模型 settings page — 输入类型 checkboxes on every provider card, and a 思考等级 field in the provider 编辑 dialog. Writes the official pi-ai input and reasoningEfforts fields.

Bayern Munich skin for the dsh web GUI: home-red/away-white canvases, real match-photo backdrops for 19 first-team players plus drawn shirt, squad-wall, Allianz-Arena and plain backdrops, switchable player and accent colour.

A read-only Cordis Inspect provider that lets an agent see the interface it is driving: outline() reports which UI regions the running shell actually rendered, with occupancy, geometry and current or past failure state; snapshot() returns one region's rendered node tree (tag, role, aria-label, own text, geometry, computed styles) addressed by slot key or CSS selector; failures() keeps a history of regions that failed to render and whether they recovered. Regions are addressed by the anchor the shell already writes for every slot, so it needs no region list and covers regions added later or contributed by other plugins. No UI, no tools, no dependencies, no network access.

Replaces personal data in conversation messages with placeholders before they reach the model (Chinese names found by context, mainland-China mobile and ID numbers, emails, bank card numbers, and terms from a user word list), shows the originals only in the local UI, and creates redacted copies of CSV/XLSX files.

Review code with Open Code Review: deterministic scope and rule resolution, judged by your own DSH model, no API key.

Ships a skill for verifying a change with the cheapest check that still yields a definite answer: an L0-L3 cost ladder from static checks to a single suite, condition polling with a timeout instead of fixed sleeps, assertions that can actually fail, and durations that are measured rather than remembered. The package also carries the two zero-dependency Node tools the skill calls - wait-until.mjs (poll a command, a file, or a port until it is ready) and measure-runtime.mjs (wall-clock timing for any command, plus a segmented timer for library use).

Recovers broken DSH turns: widens the product's own retry budget and renders the wait as a live countdown inside the same step, keeps a truncated output alive inside the same turn, and can open an opt-in continuation round when a turn has already ended; while the composer is empty it hands the send button to that continuation.

WeChat-style light theme with a dark icon rail, grey conversation list and green chat bubbles.

OpenCode Go quota in the sidebar foot under the workspace list: one cell for the most constrained window plus a hover popover with the rolling 5-hour, weekly and monthly percents, each with a usage bar, an elapsed-time marker, the remaining share and a reset countdown, refreshed every 60 seconds from OpenCode's official usage API using the key already in the DSH credential store.

基于 DeepSeek Harness 的 GitHub 插件静态安全审查预设，该项目代码由ai生成，主要框架由我搭建，通过“侦察员+审计员”双 Agent 协作、通过实验性ai自测攻防。主要功能有防死机上下文裁剪，有效防御投毒与提示词注入。包含21条安全红线、依赖树连坐排查与自动 YAML 校验，这是一名20岁非科班大学生的AI安全探索，欢迎大佬指导。本项目不能代替人工审计。请勿在生产环境或敏感凭证环境中使用。

DeepSeek Harness (DSH) plugin — see your effort and token usage by date and workspace: calendar heatmap, time-of-day analysis, workspace share, and a shareable self-contained HTML report.

Plugin marketplace inside DeepSeek Harness: a sidebar catalog tab plus agent tools (mp_search, mp_similar, mp_details, mp_install, mp_trending) backed by dsh-plugins-mp.com.

Restores Host-persisted settings when dsh web is reached through a reverse proxy on a non-loopback hostname: marks the page connection as host-owning so the Settings and model pages load instead of reporting "settings are unavailable in this browser". For dsh 0.1.7 – 0.2.x.

Reverse-engineering workbench: bridges a local IDA Pro into DeepSeek Harness through @deepseek-ai/dsh-mcp-client, exposing the ida-pro-mcp toolset (decompile, xref, rename, comment) as mcp__ida__* tools. Auto-selects idalib headless mode (analyses a binary in-process, no IDA GUI) or GUI mode (connects to the IDA plugin RPC on port 13337). Adds re_check, re_open and re_status; the bundled MCP server is a zero-dependency stdio proxy usable from any MCP client.

Restarts the running DSH process from a model tool or a bottom-right GUI control, with launchd KeepAlive detection, a detached-supervisor fallback that aborts the exit when its handshake fails, a macOS desktop restart path, and JSONL restart records correlated by arm id, pid and profile so a restart stays distinguishable from unrelated log activity.

Lets Codex delegate tasks to Desktop sessions through a local authenticated bridge and companion MCP server, with Workspace grouping, model and reasoning effort selection, event tracking, waiting, and cancellation.

Selection mode for HTML preview and browser tabs: click any element in a locally served demo page and its locator (selector, text, HTML snippet) is written into the chat input for precise AI editing.

Delegates self-contained coding subtasks to the local Claude Code subscription through the official Agent SDK and returns the result to the host session. Nineteen per-call parameters control model, thinking effort, permission mode, allowed tools, turn count and budget cap; background jobs return a jobId immediately and stream incremental output; the result carries a session handle that can be passed back as resume to continue the same conversation; commands expected to run past ~20 seconds go through the built-in mcp__dsh__shell channel, which streams output line by line without consuming model context; a Claude Code monitor panel in the session lists jobs, renders the structured process, shows live output blocks and cancels a run; the delegation procedure ships as a runtime-registered skill, so installing the plugin installs the skill.