Plugins

Independent workspace and conversation personas with adaptive styles, approved communication preferences and role-based routing to registered DSH models, including models supplied by Codex and Claude Code provider plugins.

Lossless context folding for DeepSeek Harness: the oldest span is replaced by a brief, and the originals stay in the session log.

Smart subagent routing and evolution: bind roles to any provider/model registered in DSH, including models supplied by Codex and Claude Code provider plugins, with workspace learning.

Kimi-Code-style swarm: batch-parallel subagent dispatch with adaptive scheduling, a /swarm command, and in-chat live progress rows.

One-command VPS deployment for DeepSeek Harness: a zero-dependency login gateway with automatic HTTPS that proxies the native web UI, a token-protected setup wizard, and one-click DSH upgrades with automatic rollback; as a plugin it adds Settings → VPS Deploy with version, upgrade and gateway status, or the one-command setup when DSH is not yet on a VPS.

TypeSafe Jev (System One decision model) as the jev_decide tool for DeepSeek Harness: noul, choice and score questions return calibrated probabilities; credentials reuse the DSH credential seam; 429/529 backoff retry built in.

Superself's self CLI as model-facing tools (project context, work units, reports, decisions) plus a /self command — cross-session, cross-project project state kept outside the code repo.

Windows QQ character integration kit for DSH with NapCatQQ/SnowLuma, Bilibili, local GPT-SoVITS voice, revisable memory and a dashboard; development preview requiring companion-service setup.

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

Reversible context folding plus external memory for DeepSeek Harness: tool output collapses into expandable lines, session facts become auditable records.

Blocks a tool call whose arguments lost their boundary, keeps a closing turn open when a step silently never ran so the model can re-issue it, and replaces damaged output on the model-visible surface after a fork. Zero dependencies.

Merges other sessions' context into the current turn: evidence-weighted conflict resolution, retraction of claims whose premises were retracted, trust labelling that resists cross-session prompt injection, and budget-bounded packing. Ships a benchmark.

Explain failed DeepSeek Harness agent runs locally, then produce a redacted recovery plan. No model required.

DeepSeek Harness plugin: Superself's `self` CLI as model-facing tools plus a /self command — cross-session, cross-project project state for agents.

Surveys local code and GitHub/npm for reusable implementations before development, evaluates reuse versus rewrite, and checks architecture coupling.

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.

Per-project long-term memory for DeepSeek Harness: a panel to browse, search and edit what each project knows, and a pointer injected after the first user message telling the agent to read the handoff pack. The memory store itself is a local MCP server (Python + SQLite) in the same repository; install the plugin from npm, then clone the repo, set up the MCP server per the README, and the plugin locates the checkout through DSH_RAG_ROOT or a common install path. Handoff packs are ordered for prompt-cache reuse: stable baseline first, facts appended at the end.

Pick the model your subagents run on — with a reasoning-effort ceiling and an output-token cap — enforced in code on every child DSH starts, whichever tool starts it.

Lets the model trigger compaction itself at a safe point via a compact_now tool (works mid-turn), plus a context_status tool reporting real token usage against the session's actual context window.

Deterministic loop guard: denies a tool call repeated with identical arguments and caps per-agent calls, in code outside the model; incident log lets a parent interrupt a stuck subagent.

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

DSH 智能上下文压缩插件 —— 在有限窗口内管理认知资源，让 Agent 记住真正重要的信息。 Smart context compression for DSH — managing cognitive resources within limited windows, so your Agent remembers what truly matters.