Plugins

Writes a model-generated annotation into every DSH escalation approval prompt — what the command does, what the model intends, how risky it is and why, and what each choice means — and keeps a searchable history of past approvals at /dsh-approval/history, with a diagnostics page at /dsh-approval/diag.

Rewrites agent-issued delete commands (PowerShell `Remove-Item` and its aliases, Bash `rm`/`unlink`/`rmdir`, CMD `del`/`erase`/`rd`/`rmdir`) into system recycle-bin operations on Windows, Linux and macOS, best-effort checks scripts for the same operations before they run, and keeps no permanent-delete fallback.

Routes eligible bash commands through rtk (Rust Token Killer) so tool output is compressed before it reaches the model, by asking the installed rtk to rewrite each command and adopting what it prints; when rtk is absent the executor behaves exactly like the stock one.

Records every session as one readable Markdown timeline inside the session workspace - the full request sent to the model (system prompt and plugin injections included), user input, replies, reasoning, tool calls and results, file reads and writes, web searches, skill loads, command runs and token usage - with a review page, a per-session tab and configurable capture scope.

DSH Cordis computer-use provider for the ZTE Nde desktop. npm install auto-fetches the musl binary built by computer-use-linux-zte-nde (v0.7.7-nde.3) into the package's own bin/ via postinstall; resolveCommand() resolves the cordis command path against import.meta.url so the mount works regardless of dsh web's cwd. Reserves the shared computer-use slot via ctx.computerUse.register and exposes MCP tools under mcp__computer-use-linux-nde-mcp__* (screenshot, list_windows, click, type_text, doctor, etc.). Two notable Nde fixes upstream of this provider: KWin caption+coords fallback for window targeting, and SnapshotCache that keeps AT-SPI single-wake per (app, pid) so Chrome is not repeatedly disturbed.

Zagent — unified three-role self-improvement loop with three operators. Data-RSI (daily cross-sectional cleaning: winsorize → cross-sectional standardization → median fill, plus experience extraction), Harness-RSI (evolves system prompt / memory / skills), and Model-RSI (evolves alpha training recipes via framework-native walk-forward with 2-day gap and multi-seed). Offline one-command run, GPU auto-detect. Ships one skill.

Multi-agent delivery workflow for dsh: a commander dispatches to fixed and temporary agents through a persisted task state machine, with a canvas and roster in the right sidebar.

Scans the skills DSH can load into one browsable catalog organized as collection, category and command, with a sidebar panel, click-to-insert into the composer, and custom categories and per-command notes saved outside the plugin directory.

Forces ASD-STE100 Simplified Technical English on every reply and every document. Commands: /asd100 on, /asd100 off, /asd100.

Turn-level file undo for tool writes and edits: each file is snapshotted before the write lands, and the model (an undo tool), the human (a /undo command) or a button in the assistant message action row can roll back every file a turn changed. Snapshots are written in-process rather than by shelling out, so it needs no extra sandbox permission in sessions confined to workspace-write.

Reads Claude Code and Codex plugin configurations to discover and preflight MCP servers and slash commands, with opt-in registration in DeepSeek Harness.

Use the free AtomGit quota already signed in on this machine to have AtomCode run an independent code review: the model calls the atomcode_ask tool on its own, and you can also use the /atomcode-review command to review uncommitted changes, a branch or a PR in one click. The plugin reads no API key; a usage pill below the input box shows the CodingPlan quota.

A shareable delivery receipt for a project hand-off. The `ship_receipt` tool measures what it can and records what it was told, then sorts every line into three zones: verified (evidence this run produced and that reproduces elsewhere — a command that actually ran with its exit code, a file hash for a file that is under version control, a scan that found files, a git ref present in the recorded remote), local-only (true on this machine alone — uncommitted changes, unpushed commits, an artifact no one else can see), and unverified (no evidence, including every sentence a human typed). A claim with no evidence keeps its label and leaves the body blank rather than printing the claim; declares the commit and branch, artifact byte sizes and sha256 with PNG dimensions, and the three pre-push checks.

Plan / Build mode switcher for DeepSeek Harness: an always-visible dropdown in the composer beside the permission control that switches the current session both ways through the shipped /plan and /plan off commands, plus a Default mode row in Settings → General that decides the starting mode for newly created sessions.

Adds a four-pointed-star button left of the composer's model selector that rewrites the unsent draft in place — grammar, wording, punctuation and execution order — preserving code, commands, paths, identifiers, numbers and URLs byte-for-byte, answering nothing and never overwriting text typed while it runs. A pencil under every user message reopens that message for editing without touching the draft; because the Harness session log is append-only, an edit forks the conversation before that message rather than rewriting it. A circular restart icon under every reply asks that one question again in a fresh conversation that carries none of the earlier turns. Both are refused while a turn is still answering, and disabled when the reply used a tool that can leave a trace or when the files the message named have since changed. A right-sidebar memory tree draws the conversation as turns, showing what was actually asked and answered, every answer to one question on its own line labelled original, edited or memory-free, newest first, with arrows that re-read an answer in place; right-clicking jumps to a branch or removes it from the plugin's own history.

Codex-style keyboard answers for the pending command-approval panel — 1 allows once, 2 rejects, Enter confirms the highlighted choice, arrow keys move it, and Esc rejects, with the buttons still usable by mouse.

Adds a Keyboard Shortcuts page to the DSH Settings panel with six rebindable commands — permission-mode cycling, reasoning-effort stepping, a status-page and a task-list shortcut — plus PgUp/PgDn input navigation and an optional composer Enter remap.

Reload a plugin or skill you just installed without restarting DSH. reload_plugin clears that plugin's own module cache, unloads the old instance and re-imports it, restoring the previous module if the new code throws; reload_skill forces skill directories to be re-discovered. Ships both as tools and as the /reload-plugin and /reload-skill commands.

A /review command that hands the current change set to a reviewer subagent pinned to the model you choose, with one continuing reviewer session per chat.

Session-scoped research evidence ledger with sources, linked claims, open questions, and explicit user review; provides a tool, slash command, and conversation panel, with selected-claim Markdown export that omits excerpts, review notes, and local paths by default; does not fetch sources or verify their truth.

Session-scoped delivery receipts for local artifacts: compare current file hashes with a recorded baseline, keep agent claims separate from explicit user acceptance, flag changed or unavailable files, and export a Markdown receipt through a tool, slash command, and conversation panel.

Adds /btw and /side slash commands that answer ephemeral side questions in an isolated forked sub-session without polluting the main conversation context.

Adds an enhancement chip to the composer input action row, left of the model selector: it rewrites the draft in place using the model already selected in the session, in five styles, with one-click undo and an /enhance slash command.

Replaces the built-in bash executor so every command gets an environment resolved from its own working directory: configurable PATH prepends, Python venv activation and mise shims, with a dedicated section in the Web UI settings.