Plugins

Strongly read-only, secret-aware Oracle second-opinion subagent.

Session health-check: mechanically mines session logs into structured problem tickets (retry loops, tool-error clusters, interrupted turns, token waste) over the official session-query seam; works standalone.

Secret-redacted session handoff with review, auto-start, and brief-only modes.

Conversation-level multi-agent workbench for editable task planning, real child-session observation, plan-versus-runtime comparison, and evidence-backed recovery previews; tested with DSH 0.1.1-rc.2.

Turns completed DeepSeek Harness public-content work into a browser-local visual magazine with explicit updates and reviewed one-article sharing.

Visual plugin manager for DeepSeek Harness: AI auto-translation, AI one-click summaries, AI plugin search, one-click share & install of multiple plugins, bulk updates

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

Matches prompts to installed skills for automatic activation, applies skill-declared lifecycle hooks and tool policies, and manages GitHub-hosted skills from Settings or the skill_manager tool.

Agent-agnostic skill that turns task input files into reusable structural briefs and a per-task searchable index (OpenAI Codex, Claude Code, DeepSeek Harness)

MasterGo Canvas MCP bundle with a managed local sidecar for DeepSeek Harness

Compare DeepSeek Harness, Codex, and Claude Code instruction surfaces for the same workspace.

Branch-role guard for AI coding agents: configurable integration/preview/production/archive roles, blocking direct push, force-push and delete on protected branches and agent merges into production/archive.

China hard-tech supply chain intelligence: 33-signal board, H1 earnings tracker, hit-rate track record and Q&A, via a remote MCP (mcp__cn_intel__*).

Workflow One - Visual AI workflow orchestrator for DeepSeek Harness (dsh), with multi-agent DAGs, live execution, recovery, and Feishu integration

DeepSeek Harness plugin for NI Multisim circuit generation, simulation, optimization, and lab reports via MCP

The task-center plugin set for DeepSeek Harness in one package: task ledger, model tools, human commands, wake patrol, quota-resume guard, idle-session mining, the reaper, scheduled sends, and the web kanban.

Unified Editor runtime for DeepSeek Harness, powered by MCP Apps

Telegram channel for DeepSeek Harness — one shared module serving several agents, with unforgeable sender marks, merged owner+coordinator memory, and a delivery mode you switch in a file outside the code.

Honesty guardrails on the tool pipeline: blocks a coding agent from weakening tests, swallowing errors, stubbing type checks, or deleting tests through the shell — nine deterministic hooks, each backed by a planted-failure test proving the guard can fail.

DeepSeek Harness (dsh) approval answerer backed by the agent-governance sidecar — every approval/request is decided by the deny-by-default gate, L0–L4 rules and the organizational audit chain.

Adaptive Reversible Context (ARC) for DeepSeek Harness — provider-aware, cache-conscious context governance with reversible recovery.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

OpenSpec 流程的 Agent Team：面向实施阶段的多 Agent 工作流编排。

Commitment write-gate: operator-authored rules enforced before a tool call runs — a deterministic guard tier plus an LLM-judge tier, fail-closed by default, every block written to a contradictions log.