Plugins

DSH context insight panel: Context dashboard + /context command + Context browser — one-stop context lifecycle management with categorized composition, content details, evolution trends, compaction/injection events, and stats.

Reads the session files thirty-three other coding agents on this machine already wrote — Claude Code, Codex, Cursor, VS Code Copilot Chat, opencode, OpenClaw, Hermes, Kimi, Cline, Zed and more — including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).

Brings the session history of nineteen other coding agents into DeepSeek Harness: recall, session digest and per-file history tools over a local index, plus optional automatic recall before each step.

Authorized-security DSH collection: nine work modes (redteam coordinator, pentest, code audit, binary analysis, attack-defense, AV evasion, incident response, cloud security, CTF solving) and fifteen runtime plugins, managed from a settings page with one-click deploy, install, update and uninstall.

Authorized pentest mode for DeepSeek Harness — exploration chain, assets and findings with a Web view.

Adaptive reasoning slider skin that maps each model's available reasoning efforts onto a 0–30 visual intensity scale, with synchronized portraits, background, and interface colors.

Long-term memory for DeepSeek Harness kept as plain markdown, one fact per file, readable in any editor. The `MEMORY.md` index has a hard 200-line / 25 KB cap enforced by `ctx.tools.guard()`: a write that would grow an over-cap index is denied, while a rewrite that shrinks it always passes, so an oversized index can be compacted step by step. The plugin never writes memories on its own — what is kept is decided by you and the model. The same store is also used by Claude Code, Codex, Kiro and OpenClaw.

Complete reverse-skill pack (85 SKILL.md) as a DeepSeek Harness Cordis plugin: reverse engineering, authorized pentesting and security-research skill router.

Read-only runtime management panel for the official DSH MCP client: connection status, registered tools, errors, and reconnect counts through the /mcp command and a Settings tab, with sanitized display and enable/disable patch suggestions.

fnOS 飞牛 NAS integration for DeepSeek Harness, working through the fnOS browser SDK when the Web UI runs inside an fnOS app frame: follows the NAS theme while DSH is set to system preference, lists and revokes authorized NAS directory grants in Settings, opens files and links in the matching fnOS app, and syncs the DSH page title to the fnOS app window. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-fnos`.

ACP profile plugin and standalone stdio server for using the full DSH agent from Zed and other ACP clients while sharing DSH credentials and sessions.

Cyberpunk 2077 / Night City theme: NC yellow and neon cyan identity, CRT scanlines, Kiroshi hover lock-on, combat-state HUD, synthesized typewriter and message SFX, and hidden easter eggs (relic / johnny).

Installs a multi-agent novel-writing preset for DeepSeek Harness: one conductor agent dispatches five specialized subagents — world-building, plotting, character management, prose writing, and QA review.

Text-first computer use for DSH: background Chromium control via Playwright/CDP plus accessibility-first macOS control; actions stay pinned to the right process and window without taking the user's pointer, ships a Developer ID signed, notarized Universal 2 DMG.

Adds Russian as a native option in Settings - General - Language for DeepSeek Harness, covering both the core UI and companion plugins. Localized Markdown export, in-message translation, live typography, slash-command aliases and an Alt+L layout fix, plus a settings card, all applied through a runtime locale snapshot rather than by modifying core files.

Detects prompt-injection, jailbreak, and secret-leak patterns on the agent/pre-step, tools/pre-execute, and tools/post-execute seams with allow/ask/block tiers, sanitized defend/detection audit events, a defend_report tool, and a destructive-delete command guard.

Complete port of obra/superpowers for DeepSeek Harness: 14 methodology skills via a native SkillProvider (rank 550), covering brainstorming, planning, TDD, debugging, parallel agents and more, with Chinese-localized docs and zero-build install.

NiuLai meme desktop pet — shouts "Ma～ma～" with a synced mouth when your agent finishes; 6 skins, signature actions, action-event binding, WebAudio-synthesized animal calls, hand-drawn SVG skins bundled.

Windows desktop computer-use tools (click, type, key, screenshot) with freshness checks, approval gating, process-identity verification around every action, and a sanitized audit trail.

The organ kernel of Agent-Body: plugins organized as one body. Each command is turned into a nerve impulse that deterministically innervates the organ which should handle it and names the capability to use; a heartbeat with a variable interval (faster on alerts, slower when idle) pumps operator directives, proprioception and homeostasis warnings system-wide; reflex arcs fire with zero model calls; failures go through deterministic attribution (missing tool / arguments / permission / timeout / network), a prescription, and a re-check loop, with argument errors never auto-retried. A missing organ is compensated by the one with the highest capability overlap, and tool schemas are gated by the current intent (84.7% measured reduction, reproducible in-repo). This entry is the kernel plugin package inside the agent-body repository.

Match your models and token budgets to each role, then let DSH delegate specialized subagents by task type. Covers architecture analysis, UI/UX, code implementation, codebase exploration, and documentation research, with automatic setup plus per-role reasoning effort and tool permissions.

DeepSeek Harness plugin that turns Jev judgments into three automatic actions — pruning oversized tool output to the segments relevant to the request, screening fetched pages for instructions aimed at the model, and picking which skill fits the next step — plus the jev_ask and jev_gate tools, a judgment ledger that survives restarts, and a /jev-status report. Needs a TypeSafe API key; without one it is inert and sends nothing.

Exports the session event stream to OpenTelemetry OTLP and Langfuse as sanitized, buffered traces and metrics, off by default.

Content-aware tool-result reducer: 13 reducers cut oversized output by meaning at tools/post-execute (failing tests kept, diff context dropped, JSON and CSV sampled, lint problems grouped by rule, dependency stack frames collapsed, crowded directories counted), with full originals spilled to disk behind a locator.