Plugins

Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.

LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

Web search bridge for text-only agents: ask the web or X, get structured JSON evidence (search, fetch, citations).

Adds an editable conversation canvas to DeepSeek Harness, where graph connections select context for canvas requests, with branching, merging, and local agent session imports.

Single-bundle reverse-engineering and pentest security plugin: first-turn tool narrowing, domain routing, and 33 tools covering APK, web, native binary, protocol, malware and LLM samples — with unpacking, license-bypass and anti-analysis case playbooks, an H-CoT evaluation engine (semantic routing, /hcot command), a web workbench with a ledger-driven tool shelf, an on-disk case workflow (auto-persisted evidence chain, E-numbered validated findings, post-compaction resume), GitHub-based external tool discovery, and 361 on-demand reference docs.

Connects dsh to a local SandBase Harness runtime over stdio MCP for managing agents and sessions, streaming turns, inspecting artifacts and cancelling work.

Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.

ThoughtDAG for DeepSeek Harness: turn the current DSH session into an editable thought graph on an infinite canvas.

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

A terminal UI (TUI) for DeepSeek Harness.

Installs with 27 engineering and productivity skills bundled (mattpocock/skills v1.3.1), no manual skill installation needed. Built with 40 billion tokens. This plugin delivers 10x development efficiency on top of the original skills and helps newcomers get started with the skill suite faster. GitHub issues are fully supported; Markdown is a preview; GitLab is not supported yet. Thank you for using and supporting us.

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.

Curated file-based long-term memory for DeepSeek Harness — human-readable markdown notes, one plain-file store shared across hosts (git-ignored when it lives inside a project repo), and a deterministic index cap enforced by ctx.tools.guard()

许愿特化器 · Wish Specializer — DSH 插件：让模型更出色地，不误解你的意思地，完成你的“愿望”。在短提示词+自带的Wish预设（PTC也可以）+重度的情况下，可以起到巨大的表现增益

One-click prompt enhancement (5 modes, memory chain, multi-model fallback) plus voice recognition (cloud Qwen3-ASR / offline SenseVoice, auto-stop on silence) for the composer, with one-click DSH service restart.

Claude Code-style auto-memory, natively: typed memory files (user/feedback/project/reference) with a MEMORY.md index auto-injected into the system prompt (zero footprint when empty); memory_write/read/list/delete follow Claude Code write rules (dedupe-and-update, absolute dates, cross-links); workspace-scoped and user-scoped layers, cross-process file locking with orphan-lock recovery, plain Markdown on disk, no external services, no embeddings.

Filters tool outputs, prunes stale context and discloses skills on demand for DSH 0.2.1-alpha.1.

Self-built DSH memory plugin: SQLite persistent storage + database-level audit guard (enforceAudit) + audit log. Auto-captures knowledge after conversations, agents recall via memory_recall, supports Claude Code/Codex/Cursor multi-agent sharing. Zero external dependencies.

Skill-driven harness/loop engineering workflow agent plugin.

Save every repetitive, tiresome templated prompt — one mouse click injects it into the composer and spares you the effort. 🌹

Agent Context Editor is a cross-agent plugin for manually excluding, editing, and selectively compressing AI conversation context. It also supports searching, filtering, selecting, hiding, restoring, and undoing conversation changes while preserving the original Session.

Engineering-discipline guard: requirements grill before the first edit, red/green test-evidence gates, forked adversary review, and a delivery report with a per-dimension verification workflow.