Plugins

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

Competition math (IMO/Putnam/USAMO/AIME) solved with a pure-reasoning pass, an adversarial verifier in a fresh subagent context, and calibrated confidence output (high / medium / honest "no confident solution"); optional LaTeX-to-PDF rendering.

User-defined agents with automatic routing, model failover, and squad orchestration: six model tools (agent_dispatch / agent_followup / agent_list / agent_squad / agent_import_skill / agent_upsert), no built-in agents, a native right-tab panel (Overview / Agents / Squads / History), and a floating action ball.

Explicit model routing for Main, Subagents, web_search, and image generation, plus a catalog-driven Composer and Plan Review picker with Model, Effort, Context, Fast, and Thinking variants.

DSH Web 任务面板插件：把需求、队列、子 agent 执行、自动复核、验收返工和定时执行做成一个可视化闭环。

DeepSeek Harness plugin: sound alerts for ten agent events — completion, subagent completion, background-job completion, approval, plugin approval, question, plan-review, goal-blocked, interruption, and background-job failure (browser Web Audio + system b

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

Adaptive model discovery, evaluation, tiering, and subagent routing for DeepSeek Harness.

Subagent delegation provider that runs any Claude-compatible CLI binary pointed at by a configurable executablePath field.

Automatically continues a native continuable DSH subagent once when it ends with explicit max-tokens termination, then stops.

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

Permission mode between workspace-write and full access: shell commands are checked by deterministic rules and a subagent review; irreversible or system-level actions require explicit approval.

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.

Minimal prompt x Web PTC capabilities: one-line persona, run_code SDK, subagents, Ralph, web search/fetch, and Windows Git Bash; the general-purpose workflow tool stays hidden.

Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editing.

Runtime plugin loading for the Web UI: a watched hot directory installs/updates client-plugin bundles live on every open page, no restart. Includes a right-column subagent dashboard example.

dsh plugin: unattended approval gate — subagent/scheduled/cron approval requests get a bounded answer window, then settle with a fail-closed default instead of hanging forever (per origin or per session)

Settings-UI editor that assigns per-teammate model and reasoning-effort rules for DSH native agent teams, resolved at spawn time by wrapping SubagentRuntime.startContinuable. No official files are modified.

DeepSeek Harness plugin that asks which provider and model should run each delegation before the child starts, so a subagent can go to a cheap or local route instead of the parent's.

Active wait for background subagents in DeepSeek Harness: registers a wait_subagent model tool that blocks until a named background continuable subagent settles, then returns its stop reason and closing message — optional timeout, membership gate rejects unknown ids, event-driven with zero polling. Closes the gap between run_in_background fire-and-return and the async settlement notice; wait for a background subagent without polling list_agents.

Token usage dashboard in the DSH settings page: nine metric cards (total, today, yesterday, peak day, longest session, active-day streak, active days, sessions, subagent tokens), a GitHub-style daily/weekly/cumulative heatmap, and an activity insight list, aggregated locally from session logs and projection caches, keeping token history after a session is deleted.

Role-based subagent delegation for DeepSeek Harness: one delegate tool over a folder of role files, with a roster that ships and stays overridable

Memory bridge between DeepSeek Harness and ai-memory: runs ai-memory's finalize-session when a DSH session ends, so the observations it already captured become searchable wiki pages. Skips subagents, queues concurrent session ends, and sweeps sessions abandoned by a forced restart. Requires a separately installed ai-memory server with its DSH lifecycle hooks wired by hand — ai-memory’s own install-hooks does not support DSH; this plugin only finalizes what capture has already recorded.

OpenRouter provider that reads the live /models list, so new models appear without a harness release: models sorted by name with input/output prices, per-model reasoning levels, image input, reasoning_details replay, Anthropic prompt caching, and actual spend per session including subagents from OpenRouter usage.cost, shown under the Web UI composer and by /cost.