Plugins

Multi-round deep research in the DSH sidebar: each round fans sub-questions out to parallel sub-agents, then continues from where the last round stopped and writes a cited report.

Views, creates and edits AGENTS.md and other AI rule files from the DSH settings page: the project directory chain from project root to cwd, both DSH global roots (~/.dsh and ~/.agents), and user-level rule files of 25 third-party AI tools. Markdown preview is rendered with .mdc frontmatter stripped, edits save in place with conflict detection, files whose content is identical across tools are flagged, and tools outside the built-in list are discovered heuristically. Zero runtime dependencies.

Lingshu (灵枢) is a brain-inspired persistent memory, persona and growth system for AI coding agents: pure Python standard library, zero dependencies, local-first, requires Python 3.9+. Hippocampus/cortex layered memory with forgetting curves, dream consolidation, fuzzy associative recall, emotion system, persona drift protection, knowledge base, self-authored skills, and a local web panel. Ships as a DSH bundled skill; the separately installable cordis startup-injector plugin auto-injects sessions only when Lingshu is installed at ~/.dsh/skills/lingshu (or brainPy is configured) and Python 3 is available; the optional update check contacts GitHub/Gitee.

DSH Pixel Team：DeepSeek Harness 的像素洞府多智能体团队协作与交付流水线（AgentTeams 衍生，MIT）。

Keeps an agent working continuously over long stretches: set a deadline, and if it finishes the task early, Dont-Stop automatically nudges it to keep iterating and take on the next step on its own.

DSH plugin: plain-language narration, an uncertainty gate, and mid-run interruption policy for DeepSeek Harness agents.

Delegate subtasks to Herdr-managed coding agents from DeepSeek Harness: pick the model, keep the pane, harvest the exact result, review in DSH.

精细控制全局与项目级 AGENTS.md / CLAUDE.md 注入截断的 DSH 插件，附 Web 端全局指令在线编辑器

Turns an ordinary conversation into a guided study session, keeping progress and lectures as dated files that survive a restart. A Study tab shows how far you have got and which ideas are still shaky without writing anything, and a Lectures tab lists each course's lectures as draft, dated, or archived.

Switchable identity cards (.dshcd) for DSH agents: tone, persona, and code style bound to one session's prompt section.

Hogwarts-loop as a DeepSeek Harness plugin: per-role subagent dispatch on configurable models, with a client settings page.

Local AOSP Android VM for DeepSeek Harness: preview rooted APKs at up to 60 fps, automate UIAutomator flows, and give each Agent an isolated VM.

DeepSeek Harness plugin for skill-healthcheck: keeps the skill journal while dsh runs and adds /skill-healthcheck to the chat.

Restart the Harness itself and come back: a dedicated restart_dsh tool hands the session over to the next process, which resumes it, replays the pending instruction and wakes the subagents again.

Kizuna agent letterbox: four tools that let an agent read its own inbox (mailbox status, pending letters, one letter in full) and answer a letter with completed / failed / input-required / working state. Kizuna is an agent directory with a reliable task relay: a per-agent kizuna-box on the same machine holds the inbox, retries unanswered deliveries after 3 / 10 / 30 / 60 / 120 minutes and records every delivery attempt in an append-only trail. The plugin talks to the local loopback box only and holds no credential.

Mounts the REA (Reverse Engineer Anything) MCP server through two gateway tools instead of registering its 200+ tool schemas on every request: rea_list searches the catalog or returns one tool's input schema, and rea_call invokes that tool, each call spawning a short-lived rea mcp process, so the tool definitions sent per step drop from about 780 KB (207 tools as measured in REA 6.5.0) to about 1-2 KB. When no rea entry point is found it installs rea-agents into a plugin-private directory with the pnpm bundled in DSH (dependency build scripts skipped) and links the reverse-engineer-anything and rea-gateway skills into the skills directory without overwriting existing ones.

Scientific figures as code: agents create a versioned figure IR, patch it incrementally (one node at a time — untouched objects never move), and export publication-ready, true-vector SVG / PDF / PPTX. Seven papercanvas_* tools (create, get, patch, layout, lint, render, inspect) over a deterministic engine with FC001-FC008 quality lint and CJK-aware font resolution. Verified on DSH 0.1.5-rc.3 through 0.2.2-alpha.2. By the author of dsh-sessionflow. Requires the PaperCanvas engine installed separately: Python 3.11+ and the papercanvas CLI (not yet on PyPI — install it from this repository, put it on PATH or set papercanvasBin); the plugin is a thin adapter and ships no engine.

Project-scoped SQLite memory with progressive retrieval, bounded context, a composer button and visual review. Install the repository-root DSH bundle, then run /learning-init with an absolute project path using local Python 3.10+.

Lists Claude Code and Codex sessions in the DSH Workspace browser, where they can be opened, continued, pinned, renamed and archived, with terminal, file and git tabs.

Named roles, model route guards, native configuration, and request-model visibility for official DeepSeek Harness subagents.

Provides snapshot-based research and question answering for individual A-share and US stocks.

Native generation-time Mixture-of-Agents: every turn, reference models run the same session context in parallel as pre-run drafts and one aggregator executes with full tooling; config-as-model recipes, F mirror / R trimmed views, enforced subagent gating (dual-shape session indexing), derived per-recipe vision (vision refs relay image reads to text-only aggregators), tiered cadence with separate steering and patrol rosters plus frozen reuse between beats, degeneration guard dropping degenerate reference output, anonymized model face (failure notices carry no provider identity), and cache-friendly guidance placement (the rehearsal record is pinned where it was produced instead of appended to every request, so the cached prefix covers it and each step pays only for what was added since - on by default across every cadence).

Project-level MCP servers loaded automatically: a project declares them in `.agents/mcp.json` (path and root markers configurable), and every session working inside that project mounts them in its own scope — stdio and Streamable HTTP, tools named `mcp__<server>__<tool>` — with the connections closed when the session ends. A Web UI panel lists the session's servers and their tools, and can enable or disable a project entry after confirmation, backing up and atomically rewriting the manifest.

Ships a minimal lesson ledger: brief.ps1 to look up past pitfalls, add-lesson.ps1 to record new ones, deployed into the skills directory and wired into AGENTS.md by the installer. The model checks it before working and turns what it hits into rules, so the same mistake is not made twice. This plugin watches whether that actually happens and shows the result in a tab and under the composer.