Plugins

A friendly status and context-pressure companion for DeepSeek Harness Web

Project knowledge base plugin for DeepSeek Harness: Open Knowledge Format (OKF) bundles per project, agent search/read tools, a Web UI browser/editor, and a bundled OKF authoring skill

Academic mode for DeepSeek Harness (dsh): a research persona, anti-fabrication rules for citations and data, and bilingual conventions. Pairs with dsh-ai4scholar (literature tools) and dsh-research (research skills).

DeepSeek Harness bundle that exposes Model Context Protocol (MCP) servers — stdio, streamable HTTP and legacy SSE — as native Harness tools, with a settings UI, live status, auto-reconnect, and backup/restore via local files or WebDAV.

Typed, read-only DeepSeek Harness tools for installed Kungfu Projects and Work.

Browser-automation tools for DeepSeek Harness (dsh): Chromium via playwright-core behind a security-first navigation policy re-checked on every action

Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.

DeepSeek Harness plugin: multimodal tools (image/audio/video/document understanding, transcription, image generation) via Gemini API or the local Antigravity CLI.

DeepSeek Harness (dsh) connector for OpenAgentNetwork (OAN): Gofer messages land in a connector-managed inbox and the agent answers them with oan_* tools. Join with one command.

dsh plugin that turns the iterate skill into an autonomous closed-loop harness: plan -> parallel review xN -> atomic fixes -> validate -> loop -> auto-stop, plus a dry-run pure-review mode with multi-round convergence and a meta-review that audits the rep

DSH plugin: loopback WebSocket bridge that mirrors application frontend tools onto the agent's tool registry and forwards model calls back to the application — one bridge, many apps, key-based namespace isolation

Steam-style plugin storefront: a plugin registry browsable inside DSH with one-click install, uninstall and update, plus a zero-dependency CLI and agent-callable market tools.

Cross-ecosystem aggregation data layer: syncs the GitHub dsh-plugin topic and the npm registry into one open JSON index, queried by model tools, a CLI, and a minimal stdio MCP server.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

GitHub workbench MCP server (dsh bundle): 23 MCP tools for repos, issues, PRs, code review, and search, with zero runtime dependencies and PAT/OAuth auth.

Disk-persisted execution planning for DSH: milestone/step state machines, dependency gating, an audit event stream, and a deterministic completion gate via dsh tools, CLI, or skill.

Workflow tools for the local aflare binary: generate, validate and run local-first deterministic YAML workflow DAGs (WAL crash recovery, Saga compensation) through the local aflare binary, with 300+ templates built in.

Skill for packaging DeepSeek Harness into a Tauri 2 desktop app (macOS + Windows): dual-platform install playbook, China mirror bootstrap with a subagent timeout sentinel, admin-free Windows toolchain recipe (no VS Build Tools), and three-path acceptance checklists.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a locally running Unsloth Desktop (Unsloth Studio) server through unsloth_run and unsloth_vision tools; pure HTTP client, never spawns or owns processes.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle management.

Headless-browser verification tools so the agent opens the page it just built, reads the rendered DOM and computed styles, checks the console, and screenshots the result; ships a frontend-verify skill.

Real-browser automation for dsh via an MCP server (Playwright core): navigate, click, fill, type, screenshot, and act on accessibility snapshots with numbered references - all 22 web_* tools re-exposed to the harness over stdio.

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.

Observational file-mutation rollback for the fs tools: write/edit pre-images are checkpointed as git blobs or snapshots and restored through a model-facing rollback_files tool or a /rollback command.