dsh-visual-aid
shenyan-008
dsh visual aid plugin: lets text-only main models handle images via a vision model
DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件,打造 DeepSeek Harness 生态的一站式目录。
1496 个项目,匹配「ts」
shenyan-008
dsh visual aid plugin: lets text-only main models handle images via a vision model
shililinghu
DeepSeek Harness 工作区文件上传插件:文件/zip 上传、自动解压、拖拽上传、上限可配置、中英双语 | Workspace file upload plugin for DeepSeek Harness: file & zip upload, auto-extract, drag & drop, configurable limits, zh/en UI
slow-stack
⚖️ The audit AI coding agents can't skip — deterministic facts (git history, test coverage) and six-gate claim adjudication for code security audits. Not another scanner.
starsinc1708
Map-reduce council of subagents for the DeepSeek Harness: one task fans out to independent members, their findings are deduplicated, verified by a separate panel, and reduced to a quorum report
sugarxl
Safety harness plugin for DeepSeek Harness (DSH): execution-time guard, trash-based safe_delete, composition snapshots & rollback, pre-restart validation. Standalone CLI, zero dependencies.
swaylq
Wishes that outlive the session — turn a DeepSeek Harness agent's runtime plugins into permanently installed ones. No pnpm, no network, no build authorization.
thedeveloper256
DeepSeek Harness plugin: role-based model routing — planner (root agent) on deepseek-v4-pro, delegated executor subagents on deepseek-v4-flash; ships a prompt section and a pro-flash-routing skill.
tsja2001
Token usage dashboard for DeepSeek Harness 用量仪表盘:查看缓存、上下文、请求效率、逐步骤和跨会话统计。
ttxs66666
Independent review gate for DeepSeek Harness: hand finished derivations and code to a reviewer subagent and feed its verdict back to the main model.
wellorbetter
DSH web plugin: see every session's conversation progress and token usage at a glance — all-windows overview, session analysis, cost estimation, and a token heatmap. 窗口统计插件:一屏看全所有会话的对话进度与 Token 消耗——全窗口总览、会话分析、成本估算、Token 热力图。
whaojie797-design
Generate a 10-minute readable engineering onboarding pack for any local repo. Deterministic static analysis; Python/TS-JS/Docker Compose. Agent Skill for Codex/Claude Code/Cursor.
windwhiterain
Answers an exhausted DeepSeek Harness account quota: move the session to another route of its pool when one still has allowance, and otherwise retry the same request every interval with no attempt limit.
windwhiterain
A persistent office of colleague agents for DeepSeek Harness: ordinary sessions with a roster, channels, direct messages, and delivery that wakes a colleague when something is addressed to it.
woodfood111
Composer readouts for the DeepSeek Harness: CJK-weighted draft token count, session spend at official peak/idle rates, context occupancy, and what the same usage would have cost on the costliest other model; client-only, with no host half and no credential access.
wxy
该仓库暂未提供项目说明。
xiaozhugez
A DeepSeek Harness plugin that records project pitfalls and user coding habits, injecting them into future conversations so the AI gets smarter the more you use it./一个 DeepSeek Harness 插件,记录项目踩坑和用户代码习惯,在后续对话中自动注入,让 AI 越用越懂你。
xie129716
Unofficial fork of computer-user: fixes the silent load failure on DSH >= 0.1.2, and returns screenshots as real images to vision models with an exact image->screen coordinate mapping.
xuhan242
交付物质检:排版 / AI 腔 / 敏感内容三线检查,面向 AI 协作产出的中文文档。Deliverable QA for Chinese documents: typography, AI-tone and sensitive-content checks.
xxiaoxiong
Privacy-conscious Prometheus metrics and Grafana dashboards for DeepSeek Harness
yehuioc
File-based layered memory skill pack for DeepSeek Harness and skill-driven agent runtimes: 11-layer directory model, Maps-first navigation, producer/review metadata contract, contamination guard, zero-dep scaffold/audit scripts.
ynymhrb
Durable long-horizon task runtime for DeepSeek Harness — plan, confirm, track, and resume AI work across sessions and interruptions.
youxi-huang
A configurable DeepSeek Harness plugin that adds file-reading discipline to selected GPT model prompts.
yunxiiQwQ
适用于dsh的pet插件
yunxiyang
Solidify DSH session history step by step: rewrite tool results in place to the facts the model actually kept, so long conversations stop re-sending noise every turn. Costs tokens and time: a ~770-character contract in every request, plus one extra full-context request and round-trip per step when stepSummary is on.