Plugins

Long-term memory for DSH stored as plain Markdown. Real user/assistant exchanges are captured into daily session files without a model call; an LLM pass then distils them into memories that are injected into the system prompt each turn. Retrieval is local (CJK bigram + BM25) in three levels — index, summary, full text — so the model only pays for the detail it asks for. Memories carry priorities; P0 and user-written entries are never changed automatically, and forgetting marks an entry stale instead of deleting it, so the whole chain stays auditable in status.md. Six tools cover recall, write, status, extract, feedback and the skill library; when a cluster of memories is ready to become a skill, a card appears at the end of the turn, writes the SKILL.md on click, and installs it only after you approve. Learning is on by default and follows the conversation model; turning the master switch off stops the LLM entirely while capture keeps working. Failures are surfaced in the prompt and in status.md instead of being swallowed. Pure JavaScript, no third-party runtime dependencies beyond the harness packages.

Read-only audit of the local CLI toolchain as a sidebar panel in the DSH web GUI: lists installed versions across Homebrew, npm global, pip, Rust/Bun/uv and self-updating CLIs, flags which ones have a newer release available, and shows the dependency impact for installed packages. It reports only and never runs an upgrade, so no tool on the machine is modified. The DSH plugin ships on npm as `dsh-cli-doctor`.

Route each task to one model and its review to a different one, with qualification evidence, failover and a durable journal.

Knowledge-base plugin: build auditable KB packages (references + SQL).

Product Design workflow suite for DeepSeek Harness - a router plus nine pd-* skills carrying ideas from a minimum design brief through visual directions, evidence-grounded research and audits, URL cloning, frontend builds and a blocking design-QA gate.

Nine consolidated tools that give agents full access to the stool ops CLI: server management, database query/redis, log search/tail, CI/CD deploy and history, MFA codes, git operations, notes, todos, and misc utilities (accounting, weekly reports, audit, project listing, nginx presets).

Context curation for DeepSeek Harness: content-aware tool-output slimming, dead-log sweep, pinned user requirements and in-flight work, archive-then-compact with an audit trail.

Gitee/GitHub AI employee: @ the bot on an issue (Gitee or GitHub), it clones the repo, implements the fix on the branch you name, opens a PR to that branch, and can auto-merge and auto-close the issue. v1.2 adds security scanning: configure scan repos, audit with built-in/custom prompts, deduplicate, and file new findings as issues.

Integrated visual creation toolchain for DSH: prompt reverse-engineering and audit optimization plus multi-provider image generation with async background rendering.

Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

Alternative plugin market for DSH: curated catalog plus live GitHub browsing, zh/en cross-language search, a fail-closed pre-install static security audit with an install-hook block, and per-plugin README viewing with garbled-encoding repair.

Rules execution engine for dsh: parses AGENTS.md, hard-blocks rule-violating tool calls, text-based B/D rule auditing, /guard command, version-guard for versioned files, and free-zone support (engine skips free-zone sections).

Tested-curation lab for DSH plugins: every entry passes real install/static-scan gates in an isolated environment, with full logs and reproduction commands (Chinese-first).

A structured multi-panelist review workflow for the DeepSeek Harness: N panelists score in isolated subagents, blind to each other; a chair reconciles disagreement by anchor match then Δ-level adjudication; an independent critic audits the process. Works for design, code, paper or project review.

GPT plans dependency DAGs, DeepSeek workers execute tasks with adaptive parallelism, and an optional GPT reviewer audits incremental Git diffs and drives repair rounds.

Turns the iterate skill into an autonomous closed-loop harness — plan, parallel review, atomic fixes, validate, loop, auto-stop — plus a dry-run review-only mode and a meta-review that audits the report and emits a final review report.

Rigorous open mathematics research suite: four agent skills (rigorous-open-math-research, manage-math-research-program, math-research-workflow, lean-verify) for theorem solving with adversarial audit, research program management, pipeline orchestration, and Lean 4 formalization audit; CI-verified tests and mechanical upstream sync.

Evidence-first vulnerability research workbench for DeepSeek Harness: native audit views, 29 OMV tools, Evidence.v1 findings, reproducible runs, Campaign workflows, and isolated PoC evidence.

Appends local hash-chained JSONL receipts for tool results and session events without storing prompts, tool arguments, result text, or raw session IDs.

Evidence-first operating kit: six read-only tools (capability catalog, staged workflow plans, packaged skill reader, bounded local memory search, repository release audit, release checklist) and five packaged skills - plans and audits, never remote writes.

Session execution analytics: steps, tool calls, failures, repeated actions, token usage and verification signals, rendered as text/Markdown/JSON reports.

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

Multi-agent software engineering and security audit workflow with 8 role presets (Captain, CEO, Designer, Eng Manager, Reviewer/CSO, Builder, QA Lead, Release), 4-Wave DAG scheduling across 6 default concurrency slots (1-12), PostgreSQL Wire Protocol v3 + SQLite WAL fact store, 29 skills, and a docked right-panel web console. A fork of Jueze-2019/dsh-redteam-mode that keeps its package name, mount ids and redteam_* tool names, so the two cannot be installed together. The fact store uses PostgreSQL when REDTEAM_PG_URL, DSH_PG_URL, DATABASE_URL or PGHOST is set in the environment and a local SQLite file under $DSH_HOME/redteam otherwise; role presets are written to $DSH_HOME/.agent-presets/redteam.