플러그인

24私助（24PA）: Feishu-backed personal assistant as a dsh workspace bundle.

Bridges DeepSeek Harness agent state (status, tool calls, errors, approval waits) over loopback to WhalePal, a standalone desktop pet app, so the desktop pet follows the real agent state instead of guessing from screenshots.

Telegram notifications for DeepSeek Harness questions, approval requests, and completed turns. Notification-only: one runtime file, zero runtime dependencies, no custom question cards.

Task-list staleness guard for DeepSeek Harness: watches the session event stream and counts tool calls since the last todo_write; past a configurable threshold it appends one short notice before the next step, quoting the current list, so the model writes it back to the real progress instead of leaving a stale snapshot on screen. Pure prompt injection, no blocking and no data mutation.

Runs Superpowers as an agent preset and gives each skill its own subagent model from a Settings table, so TDD, debugging and verification no longer all inherit the parent model.

Turns declared health readings — source, criterion, verdict — into one read-only verdict; an unreadable source is reported as `unknown`, never as healthy.

Holds a drafted message until the main agent is idle, no subagent is running and no background job is live, then sends it. Each hold takes an optional send time and a choice to queue, wait or steer, and lives on the host with its attachments so a restart does not lose it.

Session-context surfaces ported from T3 Code: a session-row hover card showing machine, git branch, model, agent preset, approval policy and token usage, a status pill covering pending approval, awaiting input, working, error and subagent work, a provider and model chip, a per-session header strip, a lineage breadcrumb, row-menu actions that copy the context or run DSH compaction, and a preference row in DSH Settings for choosing which facts appear. Nothing is added to the composer.

Shows the API balance of the provider behind the current model as a dsh Web sidebar card, with per-package progress bars, currency/credit-aware units, a settings tab, and subscription and credit quota monitoring.

Attention gate for DeepSeek Harness: sorts run events into blocked / terminal / progress and alerts only on the first two, holding everything non-blocking during a /focus block and delivering it when the block ends. Alerts flash the taskbar button only - no toast, no sound, no focus steal. Windows only.

TOFU BOX 伞包：一条命令装齐 tofu-zyc 的全套 dsh 插件（model-search、model-tuning、read-image-preview、shell-selector、computer-use、mcp-ui）。本包不含代码，只做两件事：以 dependencies 拉入六个子包，以 patch 层注册它们的插件行——即 dsh-base 同款 bundle 模式。装本包或单装子包，二选一，不要混装。

The Space Lens workbench as a DeepSeek Harness panel: the directory the current session is working in, scanned and explored by Space Lens itself.

Fish 自建 DSH 插件全家桶聚合包：一键插入全部本人自建插件的插件行（approval-guide / session-title-refresh / git-sync / settings-nav-order / visual-companion / agent-teams）。

即作账号：浏览器登录、账号权益与额度

多个AI Agent各干各的，消息靠你手动搬？建一个飞书群把它们拉进来，自动认领、自动交接。直连互@与Gateway路由双路线，兼容OpenClaw/AutoClaw/CherryStudio等8个框架，含8条实测踩坑，MIT

Permanently delete a DeepSeek Harness conversation and every local copy of its data: session log, derived caches, workspace index entries, spill files, and unreferenced attachments.

DeepSeek Harness deepwork mode bundle for ocmm-style agentic workflows.

WorkBuddy console for DeepSeek Harness, in one plugin: the account/model pool (merged from dsh-workbuddy-xdpool), the skill market with an in-composer skill picker, batch check-in, pending tasks, session health, history and credit usage. Bilingual.

Plays a chime when any session's response finishes (rising tone) or a question/approval is asked (falling tone), with a click-to-mute badge.

Maintained fork of dsh-prompt-enhance, brought up to DSH 0.1.7 — the plugin would not even load on current hosts (InputState.imageIds became attachmentIds, so the composer button crashed the input box; settings.get() was removed; /enhance read a session id the agent no longer exposes). Rewrites default to reasoningEffort off, which measured 252 output tokens for a draft where the model default spent 2897, and a Settings page for all 17 fields is bundled. Verified on a real 0.1.7-rc.2 host: activation, a live HTTP enhancement request, /enhance in the GUI, and the Settings page reading and persisting configuration. 204 tests.

Persistent work-progress row in the band below the composer: task completion, a progress bar, and what the agent is doing right now (generating a reply or running a tool), expandable into the full task list with turns, steps, timings and context usage.

Channel gateway for DeepSeek Harness: normalize provider traffic into one message contract, announce inbound messages as one typed event, authorize at the transport boundary.

Gear-based autonomy governor for the DeepSeek Harness agent: the entropy-sdk EntropyRuntime core (gear ladder G0-G4, utility gate, slow-up/fast-down policy, tamper-evident audit chain) bound to the Harness tool registry, with a live Web UI and paper-ready

Skill shelf for DeepSeek Harness (dsh): a sidebar panel next to Plugins and Automation that lists every skill DSH resolves, discovers and installs skills from skills.sh, upgrades them safely (previous version quarantined, never deleted), uninstalls or res