Plugins

Browser notification plugin for DeepSeek Harness - system toasts when a task finishes, a run errors, or your input is needed (question / approval / plan review), click to open the session, per-type toggles, and no false 'done' while the main session waits on its subagents.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Runs a parallel code review squad of read-only reviewer subagents (security, correctness, tests, style), each optionally on its own model, and aggregates one severity-grouped report from /review or a code_review tool call.

Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).

Project skill discovery: enumerate .dsh/skills entries with a SKILL.md present. 项目技能枚举（.dsh/skills 只读清单）

Command-triggered red/blue adversarial review for ANY plan (not quant-specific). /plan-adversarial <plan>: arms a gate that requires the agent to derive two independent subagents (red=attack, blue=defend), have them converge on a consensus plan with NO th

Exposes bounded Prometheus metrics for DSH sessions, agents, LLM calls, tools, approvals, subagents, and jobs, with a Grafana dashboard and a loopback-only endpoint by default.

Session-level root privilege bridge for DeepSeek Harness: ask mode with per-request web approval, full root mode (polkit password entry in the web UI) and fakeroot mode, with sudo or run0 --empower escalation and a configurable subagent sudo policy. It escalates real commands with sudo or run0: in ask mode each request waits for your approval; in full root mode every bash command of the session runs elevated after one password entry in the web UI. Delegated subagents need per-request approval by default (subagentPolicy: request).

Tool-surface governance for DeepSeek Harness: six scope-separated deny lists cut each agent's tool visibility through the host tools.restrict() API, unseen tool names wait in a pending gate, and dispatch_composed assembles a minimal surface from capability tags — a tasks array runs subagents in parallel, and a continued subagent keeps its original surface. Every decision goes to an append-only ledger that rotates into dated archives without ever losing history.

Defines named roles that each pair a persona with a bound model and fallback chain, and exposes one delegation tool per role, so subagents are dispatched by role name instead of a provider/model string.

Adds one system-prompt section that limits delegation to subagents and teammates to two cases: adversarial review of freshly produced output, and one-shot context reading that returns a summary.

🌐 A DeepSeek Harness plugin: pick the language beside the model selector and every reply — sessions, subagents, teammates, side chats — follows. Auto releases the pin.

Run Google Antigravity CLI (agy) as DeepSeek Harness subagents, with Gemini web Deep Research and parallel/team modes.

HTTP API for DeepSeek Harness: agents / sessions / event timeline / SSE streams / steering / messages / runs / files / questions / subagents, with archived run manifests, per-key metering and tenant isolation.

Runs a four-task, 150-point model intelligence benchmark inside DeepSeek Harness (Qin 60, Pompeii 45, Pelican 22.5, Candy 22.5): each selected model × reasoning-effort pair executes every task in its own isolated subagent session, Qin and Pelican are graded by the selected judge model against rubrics, Pompeii and Candy programmatically, and batches keep scores, artifacts and cost. Adds a 0–1000 real-world performance score per model × effort computed from local session logs across seven dimensions (output speed, first-token latency, reasoning speed, tool cadence, tool latency, tool success rate, cache hit), with baseline deltas and controlled speed runs, plus a sidebar page with ranking, performance, history and settings views. Each batch spends real tokens of the candidate and judge models, and candidate subagents get file and bash tools inside an isolated run directory.

Delivers one required user-role runtime context that makes the agent reason in Simplified Chinese and keep a whale-loli in-thinking persona (calls itself 本鱼, lazy-arrogant tone) in both reasoning and the final reply, while proper nouns, identifiers, paths, commands, URLs and error text stay verbatim; persona, extra proper nouns and context order are configurable. Enabled by default for every agent in the profile, subagents included.

A desktop pet for DeepSeek Harness: an always-on-top character and a roster panel that show what the watched conversations are doing, with seven animations, Workspace grouping, subagents drawn under their parent, and one click to open a session. Ships Windows, macOS (Intel and Apple silicon) and Linux window binaries in the package, so installing runs no install scripts and needs no build step.

Adds a DeepSeek Harness agent preset that hands implementation work to Codex subagents (auto-approved, workspace-write sandbox); the session agent only splits tasks, dispatches them and reports results. Requires DSH 0.2.2-rc.1+, the @deepseek-ai/dsh-subagent-codex bundle and a locally installed, logged-in Codex CLI.

A DeepSeek Harness agent preset where a Codex subagent analyses and decomposes the task, Claude Code subagents execute each work item, and the session only dispatches, checks and reports. Requires Codex installed and signed in locally, and Claude Code signed in locally.

Standalone DeepSeek Harness port of Google’s Elephant-Goldfish Model with seven slash commands (/egm-*) for design, documentation, and fresh-context reviews using native DSH subagents. Requires no other plugins, but it registers the same /egm-* commands as other EGM ports, so install only one EGM plugin per profile.

Human-in-the-loop self-improvement loop: one objective becomes an auditable work chain that iterates in child sessions while the main agent stays idle.

Sends one instruction to a chosen group of existing DSH sessions at once, with attachments, optional answer collection and up to eight temporary subagents.

Sends a macOS native notification when a root DSH session turn completes normally: the title is the session title and the body a sanitized, truncated preview of the reply. Subagents, cancellations and errors are skipped by default and no conversation text is stored.

Model console panel: switch the model for every conversation at once or one at a time, filter sessions by idle time, fold subagents under their parent session, and bulk archive or release sessions.