Development & Runtime

DSH Simplify is a community-maintained DeepSeek Harness plugin, not an official DeepSeek AI product. Enter /simplify in the current session to ask the Agent to improve code within your Git changes while preserving behavior. Supports DSH Web and desktop apps that include DSH Web.

Give DeepSeek Harness a real office environment. Univer Office Plugin brings spreadsheets, docs, slides, canvases, relational tables, and more into one runtime — with connected data, validation, versioned changes, and isolated worktrees for multi-agent collaboration.

Official Huawei Cloud plugin for AI agents — skills, MCP tools, safety guardrails, and cloud sandbox to help AI agents build, deploy, and operate on Huawei Cloud securely.

Catppuccin themes plus a toggleable glassmorphism skin for the DSH Web GUI: Latte, Frappé, Macchiato and Mocha registered into the native theme runtime, one-click switching with a persisted choice, and adjustable frosted glass for the top bar, sidebar, composer, stats line and trajectory view.

MCP management console for the official DeepSeek Harness MCP client: /mcp command with health diagnostics and pipeline trial calls, a Settings MCP tab with server CRUD (approval-gated writes, automatic backups) and a tool trial console over the official tool pipeline (Apache-2.0, dsh-plugin).

Self-contained browser runtime plugin for DeepSeek Harness — bundles Playwright (chromium) and OpenCLI as plugin-local dependencies, exposes a browser service and interactive browser tools.

Update management for DeepSeek Harness and its plugins: semver-aware dual-source (npm/GitHub) checks for the main program and every installed plugin, a locale-aware banner (zh/en) listing updatable items, one-click updates (the main program is backed up, integrity-checked and rolled back on failure; plugins install via a temp directory without touching other packages), and a watchdog-guarded restart after updating. The settings page adds per-plugin version lamps, live update progress, and banner/notification toggles.

Update checker plugin for the DeepSeek Harness (dsh) Web GUI: shows the current version in the session top bar, auto-checks the latest version on npm and prompts you to upgrade when a new one is available. DeepSeek Harness（dsh）Web GUI 的更新检查插件：在会话顶栏显示当前版本号，自动检查 npm 上的最新版本，有新版时提示升级。

Coding-subscription OAuth for SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code and Claude Code, plus an opt-in loopback OpenAI/Anthropic gateway: local login without pasting tokens, AUTH refresh-and-retry, grok-4.6 xhigh, and API-key route coexistence.

LLM auto-review approval answerer for DeepSeek Harness: when a session's approval policy is 'auto', sandbox escalations beyond workspace-write (sandboxpermissions: "danger-full-access" + justification) are decided without a human prompt — a human is asked only when the reviewer is unsure, and every error path fails closed.

Maintained fork of dsh-approval-gate. A neutral operation whose confirmation count has reached the threshold auto-approves when the judge is unavailable, instead of prompting a human again; approver-facing explanations are generated in Chinese from the real sandbox mode, command and paths. Also carries deterministic hard-deny for credential exfiltration and system-path destruction, judge-input redaction, a judge model candidate chain, fingerprint-scoped allow rules, and an approval view with unified diff and one-click revert.

SSH profiles, browser terminals, SFTP browsing, port forwarding, proxies, and session-scoped AI access for DeepSeek Harness.

Turns DeepSeek Harness into a server-grade multi-tenant platform: remote access + auto HTTPS, subuser permissions & token/daily quotas, sandbox enforcement, encrypted auth & audit log.

Spec-driven development discipline for dsh: five keel skills (anchor/spec/probe/build/audit), three review tools and six spec templates enforce specs-before-code, assumption verification and scope control.

Runtime Patch coordination for DeepSeek Harness plugins. A library for patching, replacing and decorating DeepSeek Harness plugins during runtime.

Chinese government document processing toolkit: GB/T 9704 format check, auto-fix, content revision (red annotation + strikethrough), template generation, Markdown-to-docx, and document header/footer/page-number injection for 24 official document types.

Complete reverse-skill pack (85 SKILL.md) as a DeepSeek Harness Cordis plugin: reverse engineering, authorized pentesting and security-research skill router.

Registers a `config_doctor` tool that checks the harness's own configuration for problems that boot silently: fields a patch dropped by whole-config replacement, patches targeting missing entry ids, and tool-name collisions. Read-only.

Read-only performance diagnostics for DeepSeek Harness: session load/restore timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via /fast, persisted as reconstructable session events with async sampling off the model path.

OpenAI Codex CLI wrapper: one-shot exec, repo review and session resume with a default read-only sandbox.

Render Mermaid fenced code blocks in DeepSeek Harness Web as SVG diagrams with a Code / Diagram toggle. The plugin supports streaming responses, dark mode, fullscreen viewing, zoom and pan, SVG export, and automatic fallback to source code when rendering fails.

A web Settings "Loop engine" switch that swaps the agent loop driving every dsh session among five engines — the built-in in-process loop plus hosted Claude Code, Codex, Pi, and Kimi Code — with zero changes to the harness; each hosted engine keeps its thinking and tool calls in the durable session transcript, takes over commands, skills, and the agent preset, and runs sandboxed through the dsh subprocess seam.

Instance manager for DSH Web: a Mini Utility Dock panel that lists every local dsh web instance the machine can see (port, PID, uptime, live session count, resident memory, version), starts a new instance on an automatically picked free port in 3080-3129 or on a port you name, opens a row in a new tab, and stops one or all of them through that instance’s own graceful shutdown (appExit). Rows also show what each instance is serving, and read-only instance logs and session summaries are one click away. Where a peer is configured, the same panel lists and queries instances on other machines over a bearer-authenticated link. Every route is loopback-guarded, and a browser-facing action must additionally pass the host’s own browser authentication.

Continual self-evolution: versioned, auditable, rollback-safe harness state (prompts, memory, skills, subagent specs) refined from session trajectories, with review gates and hot-reloaded skills.

One-command backup & restore of DSH user data with a visual Settings panel: scheduled auto-backup, sha256 verification, hardened restore with auto-rollback, typed sub-backups (--types skills), credential redaction into a local vault, GitHub sync for cross-machine moves, and an out-of-process rescue channel that works even when the host won't boot. /backup doctor checks and repairs corrupt session logs from a known-good backup; migrate-check statically predicts which sessions a host upgrade would break (frozen event-list rules, filename/generation mismatch, hardlink support, legacy credentials layout) and the credential sentinel preserves pre-migration copies before the host rewrites them; smart backup snapshots before host upgrades and quarantines corrupt logs before rotation. macOS/Linux/Windows.

Turns any current or historical session into verifiable, sanitized archives in multiple formats, manages them on disk, and gives you a compliance/traffic view — all as a dependency-free dsh bundle.

Multi-dimensional quality scoring for DeepSeek Harness plugins: scores a repo or npm package across install success (consuming dsh-test-drive results), maintenance activity, documentation completeness, security scan, and protocol compliance — every conclusion backed by real CLI evidence with audit timestamps.

Fail-closed runtime tool-call loop guard and assistant output repetition breaker for DeepSeek Harness

用于在侧边栏“设置”按钮上方显示已安装 dsh 版本的 DeepSeek Harness Web 插件。 | DeepSeek Harness Web plugin that displays the installed dsh version above the sidebar Settings button.

Subagent Director: per-subagent LLM provider/model selection with role templates for DeepSeek Harness (dsh plugin)

Multi-machine sync: keeps multiple dsh replicas consistent through one private GitCode repository — skills, sessions, settings and plugin manifests each with an independent switch; changes go through branch, PR and merge, remote-only additions are pulled back before every push so nothing is deleted, and an AI smart-align step semantically merges files both sides changed (plus one-click conflict resolution); private repos enforced, pull never overwrites local edits.

DeepSeek Harness 的社区 Grok Build Provider：官方 CLI 浏览器 OAuth、动态模型、流式工具调用与额度面板。Community Grok Build provider with official CLI OAuth, dynamic models, streaming tools, and a quota dashboard.

Starts your dsh web server at boot through home-hosted: runs that panel from the pinned copy it ships, installs or removes the panel's boot entry (systemd, launchd, XDG autostart, Windows Run key or Task Scheduler), and manages the panel's servers, boot entry and UI from a dsh settings page and six agent tools.

Isolated install-and-smoke test drives for DeepSeek Harness plugins: installs a repo or npm package into a throwaway DSH_HOME profile, verifies the bundle patch layer and boot logs, records a structured pass/fail result matrix (JSON/Markdown) for scoring pipelines, and quarantines every temp directory it owns

Context-window attribution for DSH Web: a Mini Utility Dock panel that ranks the user messages, assistant turns, reasoning blocks and tool results of a session by the tokens each one occupies, so it is clear which entries hold the window. It also shows the share by entry type, the heaviest entries across the live sessions of the host, and, where the host provides them, provider usage and the estimated system/tools/messages composition. The panel is read-only: it does not estimate cost, modify a session, or trigger compaction.

Version management for dsh: inspect the installed version against every npm channel or version line, install or downgrade in one click, stream the install log live (rollback-snapshot copy progress, npm extraction progress, elapsed time), roll back instantly from local snapshots, and automate the cycle with a policy engine (silent auto-update, execution windows, daily checks). Never stops npm mid-install — a wedged run is only stopped after an hour, and a half-committed global tree is detected and repaired from the pre-install snapshot automatically. Confirms before installing a found update, auto-restarts the host after install, and falls back to a mirror when the primary registry is unreachable.

Restart DSH: configurable restart method (Node native / legacy PowerShell), post-restart continue prompt, optional watchdog auto-relaunch.

Undo/redo & rollback system for DSH: every config change is auto-snapshotted; undo/redo/restore to any version from the WebUI or the offline CLI/GUI tools (works even when DSH fails to boot).

Fine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions, quick-tool defaults, custom rules, a bilingual approval modal with inline diff details, custom rejection reasons and a sandbox-upgrade flow.

Windows process-tree reconciler for the DSH host: samples the host process tree and the job ledger, attributes each process to the job that created it, flags unattributed and orphaned processes with a confidence level, and offers guarded termination of a whole tree. Termination is refused unless the target belongs to the DSH host tree, is re-sampled and re-checked immediately before the kill (creation time included), and contains no protected descendant, so an allowlisted PID cannot widen the kill scope.

An independent approval subagent judges every sandbox escalation, with a configurable model and an audit log.

Imports Claude Code setup into DeepSeek Harness from a native settings screen or CLI, with dry-run previews for skills, commands, agents, hooks, permission rules, and MCP config. Codex and OpenCode remain supported as secondary origins, with collision-safe apply and post-move checks.

Card-style plugin manager in Settings: enable/disable each plugin through the profile patch layer, install-source details, npm update check with one-click update, uninstall, search, and load-error badges.

Concurrency guard and monitor for DeepSeek Harness: FIFO queue when concurrent model requests reach the limit, per-day persisted stats with error-kind classification, and interruption detection for abandoned streams.

FDE toolbox bundle: installing this one plugin pulls in a curated set of common dsh plugins (git server, WebDAV mount, knowledge base, scheduled tasks, auto-resume, UI tweaks, auto-retrospection, file manager, smart titles, task board, plugin market, context trimmer, IM bridge, sidebar enhancements), with a panel showing install status and one-click gap-filling.

Noname (Sanguosha-like game) extension workshop. AI writes skill and card extensions behind confirmation gates, static validation and block-based safe writes.

DSH updater + official docs sync in Settings: one-click npm update of @deepseek-ai/dsh with live progress (npm output stream, elapsed timer, monotonic bar), multi-copy protection that only touches the running instance, source-tree mode via git pull, one-click PowerShell 7 install on Windows, incremental sync of the official docs/ with progress, and the dsh_docs_search / dsh_docs_read model tools.

@loongsuite/dsh-plugin is a standalone, open-source observability plugin for DeepSeek Harness (dsh). It observes DSH's native session, agent loop, LLM stream, and tool lifecycle, converts them into OpenTelemetry GenAI traces and metrics, and exports standard OTLP/HTTP protobuf to any compatible backend.

Community search, similarity analysis, and install/dedupe/build-it-yourself decisions for the dsh-plugin ecosystem.

Renders Wallpaper Engine scene wallpapers in real time in the browser (three.js player plus a Rust/WASM CPU particle simulation) and plays video and web wallpapers, falling back to the preview image, with no Wallpaper Engine runtime required. Scans the local Steam workshop library (431960) by auto-detection or a manual path, and offers a settings panel for wallpaper selection, library and engine directories, glow, pause and quality.

Manages DSH skills and MCP servers from the web settings: skill cards with hot enable/disable, workspace scopes, groups, batch migration and drag-and-drop import, plus stdio/HTTP MCP CRUD with connection tests, secret redaction and the unified dsh-panel CLI.

A permanent DSH plugin that bundles a developer workbench, an in-session conversation tree, and a plugin manager: build and run an LVAL project, browse its code, and keep per-program version snapshots with rollback; edit, retry, or branch any message in place, with message micro-versions; a feature manager plus a global-plugin library whose entries each carry an enable tier; cross-dialogue memory, one-shot temporary chats, and model collaboration; five network-permission tiers, mixed-model routing, a security audit, and browser control through a companion extension.

Gives DeepSeek Harness control of the Tabbit Browser: auto-loads the tabbit-browser skill on install, detects official Tabbit and Tabbit Browser releases (>= 1.9.0), checks the tabbit-cli persistent runtime, diagnoses the per-platform DSH sandbox mode needed to call the CLI, and downloads the region-matched official installer via a background job when no qualifying version is present.

Gives DeepSeek Harness control of the Tabbit Browser: auto-loads the tabbit-browser skill on install, detects official Tabbit and Tabbit Browser releases (>= 1.9.0), checks the tabbit-cli persistent runtime, diagnoses the per-platform DSH sandbox mode needed to call the CLI, and downloads the region-matched official installer via a background job when no qualifying version is present.

dsh-yolo-mode - an LLM-powered auto-approval plugin for DeepSeek Harness sandbox escalations (built-in presets + custom permission levels, fail-closed)

Complete port of obra/superpowers for DeepSeek Harness: 14 methodology skills via a native SkillProvider (rank 550), covering brainstorming, planning, TDD, debugging, parallel agents and more, with Chinese-localized docs and zero-build install.

⭐ If you like this plugin, please star it on GitHub — it shows me that the plugin is useful to you and motivates me to keep developing it. 🐛 If you find a bug or would like to request a feature , open a GitHub issue in any language — I will review your proposal and implement useful suggestions in a future plugin version.

Witness — The browser is the judge. The quality gate for agent-built web apps. Agents say done; the browser proves it. (Witness is the product name; dsh-verify is the package name — same thing.)

Skills & MCP section in Settings: browse, create, edit and delete skills with live directory watching, toggle loading of any on-disk skill through frontmatter policy keys, register local folders or GitHub repos as extra skill scan roots, edit the MCP server rows in the profile patch, import MCP config from Claude Code or Codex, and install from a curated market of skill repos and MCP servers.

A DeepSeek Harness (DSH) plugin for self-improving AI agents, providing continual learning through persistent memory, periodic review and refinement, cross-session knowledge sharing, and automatic rollback on failure. It forms a closed loop of plan → validate → apply → rollback.

Registers the DeepSeek Harness web server (dsh web) as an auto-start, self-healing background service — LaunchAgent / systemd / cron plus a 30s health-check watchdog — with seven dsh_daemon_* tools (install/uninstall/reinstall/status/start/stop/update).

Browse, enable, disable, and manage Agent Skills from Claude Code, Codex, OpenCode, Gemini, and custom directories in the DSH settings panel.

Minecraft development skills and tools for DeepSeek Harness: 8 skills covering Paper/Spigot plugins, Fabric, Forge and NeoForge mods, addon development against major mods, and Gradle/JDK build setup across Minecraft 1.7.10 through 26.x; the mc_scaffold project generator and the mc_gradle Gradle runner; an intake skill that asks for missing version/platform details before starting; four built-in subagents; and a second Minecraft Architect preset whose mc_codex tool runs the user's own Codex CLI through the codex app-server protocol to draft the skeleton, after which DSH fills the marked method bodies and verifies the build.

Windows system-tray launcher for dsh web: console-free background start (VBS/powershell chain), a tray menu with open UI / logs / icon presets / launch-at-login / restart Harness, one-click install and update of the bundled dsh-plugin-usage-meter, and a dsh plugin half that starts the tray together with the harness.

Update copilot for DeepSeek Harness: full version radar over the DSH core, bundles & every plugin (npm+git, package-centric across profiles); gated plugin updates, dual-mode gated core updates, patch-name audit. · DSH 更新助手：全量雷达 + 带闸门的插件与本体更新 + 补丁名体检

Build PowerPoint decks from a brief: plan and storyboard gates, per-page authoring through pptwise and ppt-master, a design-profile pass, page-image snapshots with a render audit, and a tool that hands those pages to an image-capable model for review.

GUI in the DSH settings panel: toggle/delete MCP servers, browse and trash skills, and list built-in plugin packages — hot-applied without restart.

A plugin can compile, pass unit tests, and still fail after publication because files are missing from the tarball, its bundle does not register in DSH, or uninstall leaves the profile broken. DSH Testkit closes that gap: it tests the artifact a user actually installs against an exact, real DSH host and retains evidence a maintainer can review.

Automatically disables a failing plugin so the rest of DSH keeps booting — by patching DSH’s own installed kernel (mount-time quarantine + self-healing), not preflight smoke-tests. Includes status tools and a one-click restore panel.

Test-stability tools: repeatedly run vitest/jest/pytest/node:test suites, classify flaky cases, keep history, maintain a quarantine manifest and health self-check.

Tauri 2 desktop application for Windows that detects (or installs) the global @deepseek-ai/dsh package, launches the DSH Web server and embeds it in its own window, with system tray management, login autostart, a global hotkey and desktop shortcuts.

Read-only DSH/Cordis composition doctor for plugin conflicts and upgrade rehearsal: scan profile manifests and patches, find duplicate rows, hook-order and UI ownership conflicts, compare redacted snapshots, diff plugin/row/hook changes, and preflight target DSH releases with explicit evidence boundaries — without mutating a real profile.

Session-bound persistent TypeScript REPL for DSH PTC mode: bindings and imports stay live across run_code calls, edit_run_code replaces one line without resending the block, module import/export syntax is adapted via AST rewriting, and durable bindings are restored from the session journal after a cold restart.

Back up your DSH profile configuration to a private GitHub Gist on a schedule, with merged restore.

DeepSeek Harness environment diagnostic tool: dsh_doctor checks env, profile, config, bundles, mount, port, health, and disk

Adds an `auto` permission preset between workspace-write and danger-full-access: a classifier grants routine sandbox escalations once, while dangerous or uncertain requests still go to a human.

本插件属于 @max-null/ 插件系列——这一系列共同构成 SSID（思灵 · Seek Soul in Darkness） 桌面体验。SSID 是整合它们的盒：dsh-capture · dsh-chat-rail · dsh-chinese-thinking · dsh-draft-polish · dsh-guardian · dsh-habit · dsh-memory · dsh-node-appearance · dsh-plugin-center · dsh-quick-toolbar · dsh-skill-mcp-center · dsh-ssid-panels · dsh-ssid-zh-ui · dsh-achievements。

DSH (DeepSeek Harness) port of obra/superpowers — 14 native skills for multi-agent software development: brainstorming, planning, TDD, systematic debugging, and code review.

MCP marketplace and management panel in the Web sidebar: one-click official templates (Apifox public/private, Apipost, MasterGo, Pixso), paste raw mcpServers JSON, and enable, edit or delete your services with hot reload.

Blocks edit/write writes that contain characters matching configurable regex rules, executed before the tool runs, with configurable messages and same-turn pwsh propagation; default rule matches full-width parentheses.

An installable community bundle that exposes the official DeepSeek Harness CLI to Multica through a versioned JSONL process protocol.

Glob-activated rule prompts for DeepSeek Harness (DSH) — a Claude Code rules.md / # Path:-style mechanism. Each rule declares glob patterns; when the agent reads or edits a matching file, the rule activates and its content (any prompt or markdown document) is injected into the conversation as a superseding snapshot.

Host-side guard that lets the write tool only create new files: when the target already exists it denies the call before execution and tells the model to use edit instead, applied to all sessions.

Service control panel in DSH Web settings: live host info (PID, versions, uptime, memory/CPU trends, active sessions), npm update banner, and a confirm-guarded graceful stop that warns when tasks are running and can wait for them to finish.

IDE-style run configurations for DSH: save LLM prompts and shell commands as reusable run configs (global or per-workspace), run them from the session header or the new-session page, and manage them via the task_run_config tool with approval-gated writes.

Deployment-configured prompt prefix. Ordered system-prompt sections render ahead of the deployment persona, and configured reference user/assistant exchanges are injected into every ordinary conversation request — as real alternating messages prepended on the request path (llm/stream interception, zero session-log writes). Static content renders byte-identically on every request, preserving prefix-cache reuse.

MCP & Skill manager: enable/disable MCP servers and skills from a Settings panel to free context in real time; optional AI middle layer (mcp_search/mcp_call) calls disabled servers on demand, with state-based visibility filtering that keeps user-enabled servers visible.

Large tool catalogs take up room before the model starts solving your task. MCP Lens keeps the standing MCP definitions small, finds relevant tools across servers, and preserves the returned data needed by the next call.

Ships a skill that documents how to build, debug and publish DSH plugins - host and client package skeleton, developing a forked plugin inside a throwaway profile, publishing to GitHub and npm, and the pitfalls found while shipping them. Installing the plugin registers the skill.

A real-time restart: the agent restarts the service (canary pre-flight passing, Canary: passed — restarting…), and the plugin's boot notification brings the very same session right back — the conversation continues automatically, no user prompt needed.

Backs up DSH profiles and mints a desktop "revival coin" that restores the harness after a failed boot or install: a boot guard runs a two-phase health check (HTTP 200 plus client render), marks good boots, isolates or rolls back bad ones, and keeps 3 rotating snapshots. Cross-platform.

Edit your /.dsh/AGENTS.md (global rules) from the DeepSeek Harness web settings panel.

Visualize the DSH process network path on Windows or WSL with layered DNS/TCP/TLS/HTTP probes, detect stale proxy configuration, and apply snapshot-guarded repairs.

🧛 Dracula theme for DeepSeek Harness (DSH): the classic dark palette — plus the Dracula Soft variant — registered into the built-in theme runtime, with a one-click skin picker in Settings → General.

Read-only insight panel for one profile: five views over the same data — config layers, plugin tree, services, tool names and models — each entry showing which layer inserted or disabled it and whether it is running.

LLM debug console for DeepSeek Harness: captures the full content of every model call at the llm/stream waterfall (options, stream chunks, usage, wire protocol) and shows it in a DevTools-style docked panel, with shared-prefix context diffing, wire-JSON reconstruction, JSON export and a runtime-tunable capture policy.

A DSH web plugin that adds a Skills page to the settings panel (opened from the sidebar-foot Settings trigger). It shows every skill the deployment can see, grouped into system / user / workspaces / preset tiers, and lets you manage them without touching the filesystem by hand:

DSH（DeepSeek Harness）技能分类管理器：自由分类 / 标签 / Collections（集合文件夹）+ 设置面板「技能管理」。 Manage and organize your agent skills by category, tags and collections in DeepSeek Harness.

Browse, search, delete, undo-delete, and update user skills from the Web settings panel; checks GitHub/Gitee Releases for newer skill versions.

Plugin manager with a rescue center: grouped enable/disable by necessity, multi update sources (npm / dshfind market / GitHub), browser-first downloads with an auto-install folder, P2P fallback, pre-boot self-check and broken-bundle quarantine.

Drive a real browser from the DeepSeek Harness chat: the agent opens pages, reads them as structured text with a numbered element list, clicks and types by ref (no CSS guessing), presses keys, navigates back/reload, waits, evaluates JS, and takes screenshots — while you watch a live draggable cockpit panel in the Web GUI and can take over at any time.

Wraps Python virtual environment management commands: reduces the network and permission problems agents hit when managing environments through terminal commands, works across operating systems, and routes installs automatically through mirrors and local proxies. The tools are strictly confined by the granted read/write permissions.

Local development service console for DSH: lists every listening service on the machine and lets users inspect, safely stop, or restart services that were started during development.

Read-only repository fact scanner kernel for DSH analysis plugins: deterministic probe / file index / modules / dependencies / entry points / symbols / graphs and git facts over a stable JSON schema (CLI + library + skill runbook).

A DeepSeek Harness (DSH) agent preset for "bootstrapping a project skeleton from scratch": ships an architect persona, a strict init runbook, per-stack template assets, and engineering standards.

月芒霜鳍鲸——让 Kimi Code 本人直接驱动 DeepSeek Harness 会话的 loop 插件。DSH 的壳，Kimi 的脑，ACP 直连，无中间层。 Moonglow Frostfin — Kimi Code itself as the agent loop of DeepSeek Harness. ACP-bridged, no middleman: DSH's shell, Kimi's brain.

A token-efficient persona runtime for DeepSeek Harness. 把人格留在界面，把智能留给模型。Measured: -67% input tokens, -66% cache reads, 0-token catgirl rendering.

Scan installed DeepSeek Harness (dsh) plugins and get a stability risk grade + fix suggestion before they break your harness — static analysis, optional isolated install verification, and machine-readable output for any agent to surface problems and remedies fast.

Read-only Sentry tools: project listing, issue search at organization or project scope, single issue detail, and the latest or a specific event with a trimmed stacktrace. Local variables, request headers and bodies, query strings, packages and secret-looking tags are removed before the event reaches the model, and oversized events degrade through source context, breadcrumbs and frames rather than failing.

Turn codebase smells into an executable, priority-ordered refactoring plan: file-length / deep-nesting / function-length / god-object heuristics plus a staged runbook (read-only, no auto-rewrite).

Plugin inventory manager for DeepSeek Harness Web: table view of installed plugins with status filters, enable/disable switches applied via HMR, config viewer/copy, uninstall and npm update reminders.

Tiered model routing plugin for DeepSeek Harness — split every session into think and build model tiers, delegate image understanding to a vision model (it only describes — your coding model does the work), and generate images from an ordinary chat model. Configured from a settings tab, no YAML editing.

Migrate Codex (OpenAI Codex CLI / Desktop) MCP servers, skills, instructions, memory and session history into DeepSeek Harness with a visual panel or CLI, with dry-run previews and secrets migrated as-is.

Security guard for DeepSeek Harness (dsh): static scan for malicious code, prompt injection and token waste, runtime interception, /scan, plugin_scan, web panel and allowlist | DeepSeek Harness 安全守卫插件：恶意代码/提示词注入静态扫描、运行时拦截、/scan、plugin_scan、Web 面板与白名单

Verification toolkit for DSH agents: evidence-based claim checking against workspace files with line citations, config validation (JSON/YAML), and read-only URL/npm/GitHub submission-readiness probes.

A developer toolkit for the DeepSeek Harness (DSH) web console: a real multi-tab PTY terminal docked under the composer plus an AI-output file browser sidebar with syntax highlighting, Markdown rendering and image preview.

DeepSeek Harness 的 Windows Web 插件，可将本地 TCP 监听回溯至进程、会话与工具调用，保障编程助手安全处理端口冲突/A Windows DSH Web plugin for DeepSeek Harness that traces local TCP listeners back to processes, Sessions, and Tool Calls for safe Coding Agent port-conflict handling.

Security review gate for DeepSeek Harness (dsh) plugins: static pre-install vetting of malicious code, vulnerabilities and supply-chain risks (with deobfuscation decoding), runtime audit, optional tool-call guard, and a one-click web review/install/uninstall panel.

One-click health check for DeepSeek Harness: 0-100 score, plain-language issue list, and safe reversible fixes via the profile's cordis.patch.yml.

Read-only MCP server that exposes the dsh-plugin-certification registry: certification grades, snapshot dates and five-dimension evidence for DeepSeek Harness (DSH) plugins. Zero runtime dependencies, stdio transport.

Skills & MCP manager in the DSH web settings: browse/enable/import/delete skills across project and user roots, and manage stdio/streamable-http MCP servers with a real connection (tools registered as mcp__<server>__<tool>, config in ~/.dsh/mcp.json).

Manual model probe for DeepSeek Harness: a session-view tab where you pick provider, API type, model and route, then send one real raw HTTP request over openai-completions, openai-responses or anthropic-messages — streaming or not — and read latency, TTFT, HTTP status, token usage and a three-layer diagnosis chain (API request / model response / strict check) on one screen, with errors in plain language.

dsh's built-in hot-reload (cordis-plugin-hmr) deliberately ignores nodemodules, so upgrading an installed plugin (dsh plugin add pkg@x) normally requires a full dsh restart to take effect. This plugin closes that gap: it watches your profile's pnpm-lock.yaml, and when an already-loaded plugin package's version changes, it swaps the running plugin in place.

Metadata-first runtime profiler for DSH agents: turn/step traces, model and tool wall-time timelines, provider usage, retries, errors, and live or historical sessions.

Read-only health clinic for the installed DSH plugin set: loader health, dependency integrity, version compatibility, install-script risk, duplicates and patch integrity, delivered as a model tool, a Settings dashboard and JSON reports.

Update checker (npm edition): a settings page comparing local and latest versions of @deepseek-ai/dsh and every installed plugin, with a red-dot nav reminder and ready-made update commands.

Ren'Py galgame production workbench: a host-side project service (write gateway plus git snapshots, a dialogue/scene dialect parser, derived progress, human-only review stamps, pinned-SDK validation and playtest, local publish) behind one seam, driven by an embedded web panel and agent tools.

Proof-carrying Skill self-evolution for DeepSeek Harness. Evolution Lab turns repeated project experience into quarantined SKILL.md candidates, evaluates baseline and candidate in isolated DSH processes, runs held-out canaries, and atomically promotes or rolls back without a manual approval queue.

Network proxy manager for DeepSeek Harness: switch between system, manual, and direct modes from a live settings UI, applied instantly.

An all-mode tool failure recorder for DeepSeek Harness: whether the agent runs in native mode or PTC (Code Mode), any tool failure is automatically written into the machine-maintained section of a skill — normalized-dedup, counted, deterministically ranked, TTL-pruned, and redacted — so the next session's model sees the most common failure causes when it loads the skill. Fail less over time.

Unifies every DSH extensibility seam behind one declarative DSL: a runtime `fabric` service, `fabric_extend`/`fabric_inspect` tools, and a capability-graph settings page.

Agent2Agent protocol v1.0 for DSH: run a standard A2A server to let other agents call this instance, connect to remote A2A agents as clients, and manage both from a visual settings page.

dsh网页端网络优化：通过缓存与压缩技术降低传输，从而大幅提升网页加载速度；同时提供网络断连指示与自动断网重连功能。非常适合追求极致性能或网络不稳定用户使用。Network optimization for the DSH web UI: reduces transfer size with caching and compression to greatly speed up page loading, plus a connection-drop indicator and automatic reconnection. Ideal for users pursuing peak performance or using unstable networks.

Loader-independent startup recovery for DSH Web that detects likely broken plugins, temporarily skips them, and restores only Boot Guard-managed changes.

Builds, tests, archives and runs an Xcode project or workspace on iOS or macOS through xcodebuild — a live filterable build log, scheme and destination pickers read from the project, and log streaming for simulators and USB devices, including iOS 16 and earlier over libimobiledevice, whose app logs stay readable while the device is locked. macOS only.

Daoist Canon (DaoZang) retrieval skill: keyword or semantic search over 285,117 scripture chunks with exact original-text extraction (line numbers, hit markers), and one-command workspace setup from the Godners/DaoZang dataset.

Runtime observability and plugin operations panel for DeepSeek Harness: shows the profile plugin tree, real Loader fiber state, capabilities/dependencies/compatibility, current-session plugin activity and upstream source/version checks, with one-click enable/disable/update/uninstall plus a standalone startup-failure diagnostics page that works while DSH is not running.

Hands standalone jobs to the Cursor CLI signed in on the same machine, with CLI readiness and proxy diagnostics, child-model settings, and a read-only connectivity test.

Prometheus metrics and a ready-to-import Grafana dashboard for DeepSeek Harness. The plugin observes public DSH lifecycle seams, keeps metric series bounded, and avoids exporting conversation or tool payloads.

Auto-adjust model reasoning effort per task (off/low/high/max): task classification, \[effort=...] markers, in-turn error escalation, DeepSeek peak-pricing-period capping with countdown notices, and manual-selection priority.

Collapsible right-docked web terminal (xterm.js) bridged to a host PTY over WebSocket: bash/zsh switching, resizable panel, and fold/unfold that keeps the session alive.

Developer quick-reference toolbox for DSH: 12 themed categories (195 entries) plus zero-dependency tools — regex tester, JSON formatter, timestamp converter, Base64/URL codec, cron generator and line diff, in a searchable settings panel.

Smart Charts skill: turns CSV/TSV/TXT/XLSX/XLS/JSON data files into standalone interactive ECharts HTML - 32 chart types including offline maps, 3 themes, no CDN. A --profile data profile (per-column dtype, cardinality, missingness, samples, statistics, entity grain, insight signals) lets the agent read the data and pick the chart itself; each chart embeds a fact sheet (plot_stats + data_preview) whose numbers are the only quotable values. LLM transform code runs in a restricted sandbox (blacklist + AST whitelist + safe builtins); --doctor self-checks the Python environment. Fully offline, ECharts bundled.

Calls your own chat.deepseek.com account as a second model from DSH: ask a question, analyze a file's line range, and check login state, plus a runtime skill and a settings-page login panel.

Boot-time guard that repairs corrupt session logs, preflights plugin composition, vm-checks client artifacts, smoke-tests host apply() and quarantines crash-causing bundles, so a broken plugin can never brick startup.

Plugin quality scorecard for DeepSeek Harness: 0-100 with grade, 6 components, fix suggestions per deduction, batch leaderboard - CLI plus an agent-callable quality_score tool.

Agent：调用 deploy 工具 … ┌─────────────────────────────────────────┐ │ 临时预览地址 │ │ https://my-site.breezy-broom.workers.dev │ │ ⏱ 必须认领，否则会被删除 · 剩余 60 minutes │ │ [打开认领链接] │ └─────────────────────────────────────────┘

Plug/unplug any DeepSeek Harness plugin cleanly — list every mounted layer (bundles + patch rows), remove with full cleanup, disable/enable without deleting, and audit for orphaned/dangling state. CLI + agent-callable unplug tool. Read-only by default; destructive operations require explicit confirmation.

Version-token-validated in-process result cache for the DSH read tool: repeated reads of unchanged files skip file I/O and line rendering, with a readcache tool for stats and clearing.

Replaces the web profile's pwsh shell executor with a subclass that rewrites every command through `rtk rewrite` before execution for token savings, running the original command unchanged on any rewrite failure (no equivalent, missing rtk, timeout) and keeping sandbox semantics intact.

Skill for packaging DeepSeek Harness into a Tauri 2 desktop app (macOS + Windows): dual-platform install playbook, China mirror bootstrap with a subagent timeout sentinel, admin-free Windows toolchain recipe (no VS Build Tools), and three-path acceptance checklists.

Exposes the DSH workspace as an HTTP API: browse, search and read files, and run natural-language agent tasks that answer with cited sources.

Zero-config per-turn git checkpoints for DeepSeek Harness (DSH). After every completed agent turn, if the session's working directory is a git repository with uncommitted changes, TurnSnap stages everything and creates one tagged [turnsnap] commit — a rollback point you never had to ask for.

Exa-backed web search provider for the ctx.web seam, with Exa Dynamic Highlights on by default and the Exa-Beta header that setting requires; exposes all eight Exa retrieval types, adds an /exa command to change highlights, search type and result count at runtime, and registers an exa_search tool that takes its own result count.

A test-insight plugin for DeepSeek Harness: builds reviewable test plans (TEST-PLAN.md) and isolated test drafts (review-only) from repository facts and change risk.

A one-click launcher for DeepSeek Harness (DSH) Web on macOS. Stop typing dsh web by hand — start, stop, and check the server from a single command, or build a Dock-able DSH.app that behaves like a normal macOS application.

Loads Claude-style plugins into DeepSeek Harness (dsh): discovers skills, commands and optional SessionStart hooks from Claude plugin directories, with hot command reload and uninstall cleanup.

Turn DSH plugins on and off directly from Settings → Plugins: an additive "Enable/Disable" tab beside the read-only "Plugin list". Flipping a toggle stops/starts the plugin immediately (no restart) and persists the change so it survives a DSH restart. 在 DSH 设置 → 插件页直接启用/停用插件：新增「启用/停用」标签页，切换开关即时停止/启动插件并持久化，重启后依旧生效。 中文文档: README.zh.md · LLM index: llms.txt · Agent guide: AGENTS.md

Toggle, delete, undo-delete, and check/update plugins from the Web settings panel; runtime enable/disable is persisted to the profile.

- a short description (from that package's package.json description) - enabled / disabled + fiber phase (running / pending / failed / …) - Start / Stop (runtime only — does not rewrite cordis.yml) - fuzzy search (name / module / id / description; subsequence match)

Parses DSH session logs to attribute AI-written files, overlays c8 coverage, and reports AI vs human code coverage with a trust score, plus a check/fix/verify tool loop for closing test gaps.

DSH plugin: exit the CLI process automatically when the Web UI closes (equivalent to Ctrl+C). Install via `dsh plugin --profile web add dsh-auto-exit`

Langfuse observability for DeepSeek Harness (DSH): per-turn trace trees aggregated by session id, with prompt versioning and evaluation.

Bridges the harmonyos-dev-mcp Python MCP server into DSH: HarmonyOS device discovery, build/install/run/uninstall, UI automation (click/input/keys/swipe/screenshot), E2E UI-tree inspection, and log/crash analysis as 18 mcp__harmonyos__* tools.

Ships a skill plus six Node scripts for a DSH install that will not come up - walking the boot stages before readiness, the plugin dependency bridges and junctions under a profile, dead or duplicated plugin rows, and the upgrade path. The scripts are diagnostics first; the rebuild helper only writes when it is given --fix.

DeepSeek Harness 插件(bundle + agent preset):让 Windows 上可用的 bash 工具限制为 Git Bash,并禁用 PowerShell。

dsh-plugin-compare compares DeepSeek Harness plugins and presets using existing sessions or controlled A/B runs. It turns recorded execution evidence into side-by-side timelines, measurable deltas, explicit success checks, and shareable comparison reports.

Connects to ADB devices and shows a live, filterable, color-coded logcat panel — floating over the app or docked under the chat composer, like Android Studio's bottom tool window. Built as a proper installable web plugin (host + browser halves).

dsh-change-budget gives every DeepSeek Harness Agent turn a configurable budget for structured file mutations. It counts distinct files, mutation calls, and submitted UTF-8 bytes before supported tools run—then rejects the first call that would cross a limit.

Speaks your agent's reports in a voice you choose, compressing long reports before speaking. Character voices need no training - a 3-10 second reference clip clones one, and community-trained models work too - and no 6.4 GB GPT-SoVITS install: the plugin installs its own runtime and voice. An existing GPT-SoVITS can be used instead, and it is the same voice model.

Track DeepSeek Harness's own releases and update it in one click. It follows the npm dist-tags (latest / next / alpha) and the GitHub releases (tag dsh-v, bilingual bodies), shows the changelog of every version between the running build and the target plus a graded risk report, then hands the install to a detached helper: move the current install aside with mv → npm install --prefix → verify what landed → relaunch with the exact same command → roll back automatically when the new build does not

Branch-aware code knowledge graph for DSH - callers, impact, trace and architecture over 158+ languages, freshness-gated, one dispatcher tool, zero MCP sessions.

- Status: living document (each section records the decision and its history) - Scope: this standalone Stent extension workspace - Upstream anchors: deepseek-harness snapshots 7b9644f2 (0812) / 9f9e2782a4 (0813), fork tip 65bcaf9902 (feat-stent)

Generate README.md for dsh plugin repositories from package.json + cordis.patch.yml + source layout — install/CLI/tools/dev/license sections, deterministic, zero runtime deps, read-only by default. CLI plus an agent-callable readme_forge tool.

Session-header button that previews and downloads the exact request frame DeepSeek Harness sends to the model: the full system prompt, the declared tools array, and the wire message array (system/user/assistant/tool-result) rebuilt from the session log via the same folds the agent loop reads.

DeepSeek Harness GitHub plugin: review PRs, triage issues, debug Actions CI, handle incoming GitHub events (webhooks + polling) via dsh-native tools.

Disk-usage audit for dsh data directories: total size, per-directory breakdown, largest files, oversized-file warnings (session logs can hit hundreds of MB) and cleanup suggestions — CLI plus an agent-callable disk_audit tool, dsh-disk-audit/v1 reports, zero runtime deps, read-only.

Generate llms.txt for dsh plugin repositories from package.json + README — AI-readable discovery files, zero runtime deps, read-only by default. CLI plus an agent-callable llms_forge tool.

Official GitHub Discussions radar for DeepSeek Harness: list, filter and search the official boards (Ideas / Q&A / Show Your Plugins! / General / Announcements / Polls) — CLI plus an agent-callable discussions_radar tool, dsh-discussions-radar/v1 reports, zero runtime deps, read-only public API.

A development safety kit: rolling config snapshots, automatic rollback on plugin failures, boot-failure rescue, and an in-settings management panel.

@memef1f1y/dsh-plugin-proxy is a DeepSeek Harness plugin that routes every in-process outbound request — LLM providers, websearch / webfetch, streamable-http MCP — through an HTTP(S) CONNECT or SOCKS5 proxy, and lets you flip the proxy on, off, or to another server at runtime, with zero restarts, by editing one section of $DSHHOME/settings.yaml (hot-reloaded) or the web settings card. The demo above is a real recording: node scripts/demo.mjs after install.

Evaluation harness for DSH plugins: YAML cases drive real headless agent runs, assert on tool calls, args, results and token usage, with a baseline gate for CI regression.

Takes the user's own .pptx template plus a course outline (lesson plan / document / plain text) and produces a courseware .pptx that adopts the template's background, color scheme, fonts, and page skeleton. Pure plugin package, no built-in API keys; the image backend must be configured by the user.

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

A hands-off safety net: directories the agent deletes go to a trash folder first and symlinks are never followed, with zero approvals.

Plugin compiler with a blueprint registry (scaffold → validate → deploy) exposed as a runtime service, three model tools, and a blueprint-gallery settings page.

A Windows system-tray launcher for DeepSeek Harness Web. No install step: download (or clone) the repo, edit a small config block, and run the script. The tray icon controls the running server — start / stop / restart / open the Web UI / tail logs.

🤖 [AI Agent 一键接入指引 / AI Auto-Onboarding Instruction] Dear AI Agent, if you are reading this repository to install it into a DSH profile, execute the following: dsh plugin --profile web add , restart dsh web, then confirm with dsh --profile web --dump-config | grep genome. Once installed, read skills/genome/SKILL.md for the management & evolution methodology. 数据目录 /.dsh/genome/，Web UI 设置页「基因组」可观测可操控。

Circuit breaker for idle agent turns: watches agent/assistant-stream and cancels a turn that produces only reasoning — no text and no tool call — after 45s, after 80000 reasoning characters, or on a degenerate repetition pattern (exact repeat unit, sentence-template repeat, sparse repeat, or 6-gram density). On trip it injects a continue instruction that requires the next action to be a tool call, and ships 11 regression cases plus per-gate tuning.

Quality suite: background tsc --noEmit diagnostics fed back after the agent edits TypeScript, plus a /code-review command running five parallel review lenses with confidence scoring; absorbs dsh-code-check and dsh-command-code-review.

Dependency-topology guard: pre-install conflict prediction and post-install detection of duplicate @deepseek-ai/dsh-* copies, version drift, and vendored core services that cause Symbol-key crashes like "Cannot read properties of undefined (reading 'prepare')".

Self-healing runtime layer: a resource control loop with strategy switching and repair escalation, error-storm and fiber-failure insight, cross-session knowledge carry-over, a self-healing dashboard and 7 tools.

Plugin-combination analysis for the DeepSeek Harness: dependency trees, conflict detection, risk scoring with prediction, visualization, and combination simulation.

dsh-api is a first-party plugin for [DeepSeek Harness (dsh)][dsh] that exposes dsh's own internal capabilities on the loopback HTTP socket dsh is already listening on. Any process on the same machine — a desktop wrapper, a browser extension, a CLI, an editor integration — can drive dsh through one uniform entry point, instead of reaching into its in-process services directly.

Infrastructure as code: gated plan/apply, state and output inspection, and configuration validation via the terraform CLI.

Windows boot autostart and one-click restart for the DSH service, from inside DSH: a resident supervisor that outlives the host, so a failed restart cannot leave DSH down; DSH spawned attached to a hidden console the supervisor owns, so no console window appears; plus a restart button, the current tokenised access URL and an optional post-start hook.

DSH web plugin: skill manager in the Settings sidebar - list/enable/disable, folder batch import with conflict prompts, state-driven one-click DSH-spec check & auto-fix, system/project scope labels.

- GitLab API: Create/review/close merge requests, manage tags, monitor CI/CD pipelines with per-job detail - Kubernetes API: Deployment status, pod lists, events, logs, image change and rollout restart - Dashboard UI: Dual-card switcher (GitLab server / project, kubeconfig / context / namespace) with persisted config - Multi-config: Multiple GitLab servers and multiple kubeconfigs, switchable from both the dashboard and settings - Webhook + Alert engine: GitLab webhook �?followup() notification;

Vets local, npm, and GitHub plugin source before installation, blocks configured high-risk tool calls at runtime, audits output secret patterns, and writes HMAC-chained local audit logs.

Cadence SKILL (Virtuoso Lisp) assistant for EDA engineers: official-doc-anchored API lookup (3557 entries across 5 IC6.1.8 manuals, signature confidence levels, never invents APIs) plus zero-execution static analysis driven by a lexical depth coordinate system — iterator-safe deletion with position-sensitive copy() protection, printf placeholder/argument reconciliation, in-loop nth O(N^2) detection, deprecated APIs with page refs, dangerous-intent interception and CIW error-log triage. Host half has zero third-party dependencies.