Plugins
Browse, filter, and install DeepSeek-Harness plugins.
12 plugins found
rotifer-playground (rotifer)
rotifer-protocol/rotifer-playground
Rotifer Protocol skills plus the Rotifer MCP server, configured as instances of DSH's own skill provider and MCP client: search Genes, compare them on Arena rankings, install or roll back Genes in the local project, and create and run local Agents. The MCP server is version-pinned and limited to its evolve tool set, which leaves out publishing and login.
dsh-agent-arena
leemancheung/dsh-agent-arena
Compares coding agents in isolated Git worktrees with deterministic validation, scoring, and explicit winner application.
dsh-shooter
huangxn29/dsh-shooter
A top-down arena shooter that lives in the DSH sidebar: an autopilot AI plays the blue whale-fish hero for you while the dsh-pet desktop pet narrates each wave out loud, and combos, boss waves every fifth wave, in-run upgrade choices, a local leaderboard, achievements, skins and a floating desk widget (a fish that keeps playing in the corner, click to pet, double-click to open) keep the run going while you work.
dsh-model-rank
jingxuan-wh/dsh-model-rank
Sidebar leaderboard for DeepSeek Harness (DSH): LMArena blind-test ratings, Artificial Analysis intelligence index, LiveBench 2.0 capability, OpenRouter weekly/monthly usage and market share, price, speed and context — plus a local token-usage dashboard built from your own session logs (tokens, estimated cost, per-model ranking), model detail drawers and CSV export. Daily snapshot, instant open, no API key; locally configured models are highlighted.
dsh-eval-guard
huhu23333/dsh-eval-guard
Evaluation guard for DSH: workspace-only filesystem, no network/subagents, wall-clock limits, and task installation for meow-ai-arena and benchmark tasks.
dsh-fx-arena
koishi-fumo-code/dsh-fx-arena
Simulated FX trading arena played against an algorithmic whale-chan opponent: a live canvas candlestick chart over five instruments (EUR/TOKEN, GBP/TOKEN, TOKEN/JPY, gold, and Whale/TOKEN, her own coin she never shorts), selectable leverage from 10x to 500x, and two modes — a timed mode with 90s to 500s rounds settled on equity, and an untimed goal mode that starts with $300,000 and ends when someone first reaches $20M or goes into debt (equity below zero, no maintenance margin). The match runs in a module-level engine, so switching to a conversation does not stop it or restart it. Margin and spread are modeled, prices are a local random walk with occasional news shocks, and nothing touches the network or real money.
dsh-jcc-theme
liuyaguang8023/dsh-jcc-theme
Unofficial Golden Spatula fan theme for the DSH Web GUI: an original hextech arena backdrop with a golden spatula crest (a parchment chart in light mode), four accent palettes (gold, cyan, violet, blue), a hex-board lattice, an optional aurora-and-gold-dust ambience, soft or sharp corners, a three-choice augment draft with a local 12-card codex, and a floating hex-core panel that can turn the theme off without uninstalling.
dsh-plugins
hj01857655/dsh-plugins
Cross-session memory for your dsh agent: remembered, recalled, and re-verified instead of assumed.
dsh-client-ui-skin-bayern
dirtywork22/dsh-client-ui-skin-bayern
Bayern Munich skin for the dsh web GUI: home-red/away-white canvases, real match-photo backdrops for 19 first-team players plus drawn shirt, squad-wall, Allianz-Arena and plain backdrops, switchable player and accent colour.
dsh-model-arena
hj01857655/dsh-model-arena
Run the same prompt through every model you have, and see the difference without squinting.
dsh-evidence-arena
shengshifantang/dsh-evidence-arena
Evidence-first multi-model coding comparison workbench for DeepSeek Harness
dsh-evolution-lab
jaydong9130/dsh-evolution-lab
Evidence-backed Skill self-evolution for DeepSeek Harness: redacted trajectory learning, quarantined proposals, arena validation, canary monitoring, automatic rollback.