← Leaderboard / Models / Plugin
Last repository activity August 16, 2026 · Created July 25, 2026

GCS-ZHN/@gcszhn/mcp-sentinel-deepseek-harness-plugin

“DeepSeek Harness plugin that acts as a sentinel between the AI agent and MCP servers — polling long-running tasks on the agent's behalf so that token-costly status loops never enter the LLM inference path.”

Star rank
Pending
install verification
In Models
Pending
install verification
Stars
3
GitHub repository
Forks
0
GitHub repository
Watchers
3
GitHub subscribers
Open on GitHub ↗
Description

DeepSeek Harness plugin that acts as a sentinel between the AI agent and MCP servers — polling long-running tasks on the agent's behalf so that token-costly status loops never enter the LLM inference path.

30 days of GitHub stars
+0 stars
+0% observed change
+0
Jul 18Aug 1Aug 16
Also in this category
4 items
Models

ccch1mneyyy/working-activity

Live model working-status line: playful copy, running tool, turn elapsed — for TUI prompt and Web UI.

☆ 645
Models

060625dfy/dsh-prompt-boost

Trae-style input booster for the dsh web GUI: a sparkle (✨) button beside the model selector optimizes the typed draft into a high-quality, faithful, directly executable prompt via the session's default model; after optimization the button becomes an undo (↩) icon that restores the original input. Zero-build pure-JS plugin: the host half serves /api/prompt-boost/optimize (llm.stream), the browser half registers the conversation.input.right slot.

☆ 0
Models

0lidaxiang/dsh-plugin-greet

A beginner-friendly configurable greet tool plugin for DeepSeek Harness.

☆ 5
Models

1264459640/dsh-trellis

Self-contained Trellis workflow trigger for DeepSeek Harness: per-turn breadcrumb injection via agent/pre-step, a bundled skill provider, and DSH-native task/phase state resolution. No Trellis AGPL code is vendored; workflow semantics are rewritten and licensed MIT.

☆ 0