Plugins

Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.

Lets the agent start a conversation on its own, using a local dice roll on a set interval to decide whether to speak into a chosen session, with quiet hours and a dry-run mode.

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.

Repair DeepSeek Harness sessions that refuse to load, with a sidebar Session surgeon overlay and dry-run repair.

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.

Patch-style file editing: one apply_patch tool accepting git/unified diff (default) and Codex apply_patch syntax (opt-in), applying every change all-or-nothing after a full read-only verification pass, with sandbox-aware delete and move and a dry-run mode.

Automated daily content pipeline for Insta360 GO 3S: BLE/WiFi remote capture of aquarium footage, wireless import, ffmpeg quality evaluation with decision log, Auto editing (segment selection, TTS narration, music, subtitles), and Bilibili upload via biliup (dry-run by default).

DSH-native uv environment manager: create, sync and run Python virtualenvs from the settings tab, with pip fallback, read-only conda visibility and a dry-run project sync preview.

Economics-first journal/working-paper monitor for DeepSeek Harness: NBER RSS + arXiv econ (4 categories) + Chinese econ journals (Shi Jie Jing Ji via Magtech, Zhong Guo Nong Cun Guan Cha, Cai Mao Jing Ji, Zhong Guo Ren Kou Ke Xue, Jing Ji Guan Li via ajcass) fetch, keyword filter, dry-run/Webhook push, dedup persistence, and schedule_create-compatible briefing.

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.

Turns the iterate skill into an autonomous closed-loop harness — plan, parallel review, atomic fixes, validate, loop, auto-stop — plus a dry-run review-only mode and a meta-review that audits the report and emits a final review report.

Removes subagent entries and orphaned projection caches from DeepSeek Harness session logs after the app quits, always dry-run first and with a full backup.

Scans the whole C drive and classifies every large folder into A/B/C/D/E/P (safe cache / relocatable / junction-movable / abandoned software / config-memory redline / personal files), then deletes, moves, or redirects on demand — with strong redline protection, dry-run preview and undo. Unknown software decided by LLM fallback + human confirmation. Works on DeepSeek Harness 0.1.7 through 0.2.x, tested on 0.2.0-rc.1.

Applies structured unified diffs (git format) to the real filesystem: multi-file/hunk parsing, fuzzy hunk location with line-offset correction, all-or-nothing application with typed conflict reports, reverse-patch undo journal and dry-run - four patch_* dsh tools plus a CLI.

Exits the dsh CLI process automatically when the Web UI closes, with a configurable grace period and dry-run mode.

Jira Cloud issue-tracker integration exposing eight model tools for issue search, project and transition lookup, creation, updates, comments, and transitions; writes are opt-in and support dry-run.

The missing companion CLI for DeepSeek Harness (dsh): manage MCP servers with one command — add/list/remove/test with dry-run connection checks, plus one-shot import from Claude Code / Codex. Also mounts as a dsh plugin so the agent can manage MCP itself.

Always-on AI teammate: hand it a recurring task in one sentence; dry-run rehearsal by default, snapshot before every real run, one-click rollback, CNY budget circuit-breaker, per-run cost transparency.

Keeps the /tmp cleanup daemon alive: an in-process watchdog revives it within about two minutes after Android kills it, runs the due cleanup inside dsh while it stays down, and adds a settings page for status, config, clean and dry-run. The cleaner ships inside the package (bin/tmp-clean, Python 3), so no extra install step is needed.

Let the agent restart its own DSH host: schedule a self-restart, finish the turn first, then a detached helper stops and relaunches the app and reports what happened. Dry-run, a status check, and an optional "when can I blink" confirmation are built in.

Session deletion for DeepSeek Harness: a sidebar menu item, a workspace-grouped batch cleanup panel and a session_delete tool (dry-run by default). Deletes session logs, projection cache, workspace-registry references and derived search indexes, and cascades to all subagent sessions.

Describe the persona you want and the agent writes it: nickname, bio, taglines and links come from the host model, the avatar comes from your local asset library (or a path you give), then it fills your profile page and hands the picture to the site's own uploader. Dry-run by default - it only touches profile fields, never passwords or security settings.

Context firewall for DeepSeek Harness: credentials in successful plain-text tool results become opaque ⟦cloak:category:n⟧ placeholders before they reach the model, with originals kept only in a process-memory, agent-scoped vault. 36 built-in signature families (shared with the cloakpack git pre-push guard), key-name rules for unknown formats, custom regex rules, dry-run mode, an audit log, and the /cloak command.

Conflict diagnosis and repair for DeepSeek Harness plugins. Builds a capability graph of the running Loader profile and of the on-disk cordis.patch.yml layers, comparing imports, peer ranges and config against the host that is ACTUALLY running rather than the profile's possibly-stale copies, and reports the conflicts that fail silently: a fiber stuck PENDING on a service no plugin provides, a browser half injecting a client module nothing provides, a tool id two plugins both register, duplicate Loader entry ids, a row disabled by one layer and re-inserted by another, an import of a host subpath the running host does not export, and a cycle among inject declarations. Every finding carries its evidence, a confidence grade for who owns a name, and a repair with a risk grade — verify it with a dry-run difference table, or take the individual .patch.yml files that --fix-out writes (never auto-loaded, so picking wrong breaks nothing).