Plugins

Drop-in agent loop with bounded-slice context engine (cordis).

Role-based AI swarms for DeepSeek Harness: an architect plans, parallel builders execute, reviewers gate quality, and an integrator ships. Per-role model pinning with fallback chains, review loops, evidence contracts, human-gated reviews, quota-aware pause/resume, and a live kanban + flow chart in the web GUI. 40 tests; installs from GitHub or npm.

Publishes the DSH Web GUI to LAN or internet with dsh kept on loopback. Every source must sign in for an HMAC session cookie unless passwordless LAN is opted into. Adds self-signed or custom TLS, a secureCookies override for plaintext-HTTP proxies, and a UUID shim for plain-HTTP origins.

Use DSH from iPhone/iPad: an explicit-opt-in LAN reverse proxy (Host/Origin rewrite through the loopback trust fence, WebSocket upgrades included), iOS PWA chrome (home-screen icon, standalone meta, viewport-fit), and touch/mobile CSS (safe areas, keyboard lifting, composer row fit).

Adversarial checkup → fix → review loop toolset.

Chrome and Edge browser control that drives the real logged-in profile, tabs and cookies through an MV3 extension and a loopback Bridge, exposing browser_* tools, a Skill and /chrome commands.

DSH Web 暂停插件：agent 完成一轮工具交互、正要发出下一次模型请求之前暂停，保持 composer 输入框可用，人类以回车/发送放行并可携带补充文字；此暂停不打断任何在途 API 调用，模型上下文始终完整、无感知。纯插件自包含，不改 DSH 源码。

Identity-gated Tailscale access to the Web GUI with dsh still bound to loopback: a 127.0.0.1 proxy published by `tailscale serve` admits a request only when the Tailscale login it stamps is allowed, with an optional per-device allowlist, so the privileged /api methods behind the loopback check — Settings, Models, Plugins — answer without dsh being told to trust a remote host.

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.

Mobile remote suite: Host pairing plugin with QR offer, loopback Host Gateway, encrypted Tunnel and same-LAN WebRTC Direct, plus an Android APK in this repo.

Deep research as an agent mode: one reviewed loop that plans, researches in adaptive parallel rounds driven by the gaps the researchers themselves declare, synthesises a cited report and then reviews it adversarially, instead of a script the model rewrites per call. Questions the round budget never reached are named in the report rather than dropped.

Use Kimi Code as the DSH agent loop over ACP, with approvals, slash commands, and local/remote (ssh+tmux) session attach.

Telegram duty gateway: phone-message task loop on a dedicated duty session, global approval forwarding with inline approve/reject buttons, telegram_ask choice questions, duty/local toggle with a web duty banner, zh/en messages, zero idle tokens.

Commander mode for the dsh web GUI: a one-click session header button injects a protocol brief into the session, then parses and auto-executes task blocks in the model reply — separating the strategist loop from worker loops via a visible badge.

Fan-made wallpaper plugin themed on the streamer Zhang Shunfei: full-screen high-definition rotating colorful pegasus GIF wallpaper with theme blending and prominence control, plus a Bilibili music player (add songs by pasting a link, delete, volume, seek, single/list/shuffle loop, and a sidebar mini player).

AgentDuel is a code-battle game. This plugin lets you complete the entire game loop inside DSH: manage deathmatch characters and capture-the-flag teams, submit agent code, start battles, watch replays, and use DSH conversations to keep improving agents based on battle results.

Free voice closed loop for the Web UI: browser SpeechRecognition mic input with live interim results plus read-aloud speaker buttons and auto-read for assistant replies, zero configuration and no API key.

Fail-closed Feishu (Lark) channel bridge: chat with a bot, get dsh agent turns back — with opt-in human-in-the-loop tool approval (Allow/Deny cards before every bash call, fail-closed timeout). Official-Python-SDK-only integration (exact-pinned); deny-by-default allowlist, webhook signature/timestamp/replay verification, per-chat sticky sessions; daily latest-SDK compatibility canary; bilingual docs.

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.

A judgment core for DeepSeek Harness: a cognition loop that gives every decision a source and attribution and drives planning to a close, hippocampus memory that condenses running experience into reusable knowledge, and a customizable persona card (name, personality, communication style). Requires DSH ^0.1.0-rc.7.

Plan-usage pet for the DSH web GUI: a floating skeletal-animated character reports quota in a speech bubble, auto-matching the configured provider (OpenCode Go, Command Code, DeepSeek) to show a plan percentage or an account balance, and falling back to local token stats when the provider API is unavailable; draggable, wheel-scalable (90-260px), synthesized click sounds, loopback-only routes.

Zero-config lint feedback loop for JS/TS, Python, Go and Rust: lint_diagnostics / lint_workspace_errors / lint_fix tools driven by the repo's own eslint / biome / ruff / golangci-lint / cargo clippy (auto-detected from config files, repo-local node_modules/.bin resolved first, nothing bundled), plus an auto-injected post-edit findings delta on the harness fs/observed event and a bounded completion gate — edit → lint → auto-repair with one lint_fix call for dsh agents.

Agent discipline guard for DeepSeek Harness: four gates enforced at the harness boundary — loop circuit-breaker, token-cost fuse, route-switch warning, plan approval — where prompt-level reminders can't reach, so an agent can no longer burn a weekly quota in minutes; one-click 🛡 chip, hot-reloadable thresholds, and presets from invisible-but-armored to warn-only.

Three-tier agent memory harness: L1 always-on CLAUDE.md, L2 index, L3 detail skeleton with templates, a gate that blocks writes to protected files without a one-time approval token, zero-judgement event logging, weekly distillation, and a TDD execution-loop skill.