Plugins

Edit the host-wide global instructions (~/.dsh/AGENTS.md) from a dedicated Customize page in Settings - every session on this machine applies them.

Heartbeat loop for DeepSeek Harness: every 20 minutes (by default) the agent wakes on its own to keep a local profile of your interests and preferences, search the web for things you care about, and keep what it finds. When it has something worth sharing, it sends a short package of notes to the sessions you link it to. A set of rules in code - quiet hours, busy windows, a daily limit, a cooldown - decides whether it may speak at all, and the agent in that session decides whether to actually say anything. Windows only.

Portable agent knowledge base in plain OKF v0.2 Markdown: 13 wiki_* read/write tools, progressive disclosure, backlinks, gated writes via AGENTS.md rules, auto index/log maintenance, linting, and named multi-bundle switching (session-level or global).

Per-step model router: named presets with ordered image/keyword-group rules route each agent step across every mounted provider and model, adding collaboration flows for image transcription, an image guard, a multi-plan quota panel, and per-step decision observability.

Local-first fiction workspace that links outlines, chapters, characters, timelines, writing rules, and continuity checks to the conversation.

CC-style auto-approval for DeepSeek Harness: deterministic deny/allow rules plus a two-stage allow/reject classifier with a circuit breaker and denial guidance.

Native desktop and webhook notifications for turn completions, failures, and approval requests, with outcome filters, content rules, privacy controls, and retrying delivery.

Environment housekeeper for the agent: toolchain inventory (node/pnpm/git/gh/ffmpeg/browsers), scratch/cache scan with whitelist-guarded one-click cleanup, and the machine rules file (AGENTS.md) editor - all in the Web GUI settings.

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

12 tested engineering skills (git commit, code review, test-first, plugin dev, debugging, changelog, PR review, task breakdown, and more): every SKILL.md passes a format validator aligned with the official skill rules plus an isolated load smoke test.

One stylesheet that retypesets the DSH conversation to measured Codex metrics: 14/22 px body, tighter headings, lists and blocks, a rounded quote bar, and Tidy Tables with a themed header, row/column rules, full-width short tables and contained scrolling for wide tables; no settings or DOM rewriting, with real before/after captures.

Preset engineering workflows for DeepSeek Harness: a dev_task tool that gates stage transitions, artifacts, verification, review and commit scope, plus a web workbench for installing project or user skills and rules.

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.

Rate-limits LLM requests per provider and per model using a reservation-based token bucket, with queue or reject modes, plus gateway identity rules that rewrite user-agent and inject custom headers.

Inject rules when needed, without wasting context. DSH port of opencode-stream-rules.

Keep declared workspace subpaths (e.g. .git) read-only, honor a read-only rules file at the workspace root, grant extra writable roots under workspace-write, and let the model request session-scoped write access; enforced for sandboxed CLI commands and the write/edit tools.

Injects durable user-set must-do and must-not requirements into the model at conversation start.

An accumulated design-taste corpus for DSH agents: feed good and bad examples, distill principles, and review new designs against learned judgment rather than a fixed ruleset.

Task-driven plugin equip engine: dual retrieval (curated rules + LLM semantic), combo scoring (synergy/conflict/cost/trust), conflict detection and install-command export.

Rules execution engine for dsh: parses AGENTS.md, hard-blocks rule-violating tool calls, text-based B/D rule auditing, /guard command, version-guard for versioned files, and free-zone support (engine skips free-zone sections).

One-click ✨ polish button for the composer: rewrites prompts and drafts with WorkBuddy humanizer-style rules (kills AI-flavored phrasing, varies rhythm, mode-aware for instructions/questions/prose) via free Zhipu GLM-4.5-Flash or any OpenAI-compatible API, falling back to offline local rules.

Settings section for archived sessions: browse by workspace, search, batch unarchive with the sidebar updating live, and optional auto-archive rules (idle days, keep-last-N per workspace) with a dry-run preview — plus a left-edge turn rail for jumping between turns of long conversations and ↑/↓ input history in the composer.

Private, per-project system-prompt rules for DeepSeek Harness — matched by git remote URL, repo path, or cwd prefix; worktree-aware; never committed to the repository.

String-matches tool-call input arguments, blocks dangerous tool calls (deny) or allows them with an injected warning (warn), and ships a full rules-management panel.