by boring-cuzzz

Startup & turn-completion chimes for the DeepSeek Harness desktop app, with an in-app control panel and switchable sound library (Windows, zero dependencies).

by Yazzyk

DeepSeek Harness (dsh) plugin: manually select files or directories in the Web GUI to block the agent's read, search, write, and edit access to them. A dsh plugin that denies an agent read/search/write/edit access to chosen files and directories, picked from the plugin's own We

by 863683348

Ecosystem-wide plugin health audit: syncs the dsh-plugin topic into a local scored catalog (maintenance / docs / npm + weekly downloads / ecosystem, 0-100, A-D), static security scan with high-finding

by Q1hangL

Cooperative timeout guard for ask_user_question: lost or unanswered questions resolve as a structured ASK_TIMEOUT instead of hanging the turn forever.

by zmh2000829

No project description is available for this repository yet.

by taxueseek

Integrated visual creation toolchain for DSH: prompt reverse-engineering and audit optimization plus multi-provider image generation with async background rendering.

by softspark

DeepSeek Harness provider for locally authenticated Codex app-server access through a ChatGPT subscription.

by ang-XWBWZ

AI approval answerer for DeepSeek Harness (DSH) using the unified LLM route with fail-closed policy checks.

by taxueseek

Static-only plugin gate and clinic for DSH: audit before install, hash-and-capability lock after install, local fingerprint peer search over GitHub topic:dsh-plugin, and mechanical detox. Never execut

by ChenYiming-aaa

DeepSeek Harness (DSH) GitHub Integration Plugin: After a single authentication (GITHUB_TOKEN or OAuth Device Flow), the model can directly invoke 45 github_* tools to create a repo, push, open a PR, manage issues, search code, and more; routine read/write operations are allowed through, while dangerous operations (delete/force push/merge PR/close issue) keep an approval gate; tokens are stored in the DSH credentials service and never written to logs. Comparable to opencode's GitHub MCP.

by Mr-Neutr0n

Clinical documentation and reference bundle for healthcare professionals: SOAP/APSO progress notes, admission H&P, SBAR/I-PASS handover, discharge summaries, Safe Harbor de-identification, patient-ins

by 3likofj

This plugin is a programmable memory orchestration layer + self-evolving engine on DSH

by Hyperionjust

No project description is available for this repository yet.

by suuuuuu-1

Bidirectional Discord bridge and remote controller for DeepSeek Harness

by 173787247

Hard-stop consecutive identical tool calls after a configurable streak so the agent cannot spin in place.

by Kevinwu901113

Dots-style always-on agent for DeepSeek Harness (dsh): its own computer, reachable over IM, scheduled work, hard budget limits

by W-SING-HUNG

Job Resume Studio: Paste the JD, and AI rewrites your resume to match the position — based only on real content, no fabrication — DeepSeek Harness Plugin

by vitas

Cut LLM costs: a Jev (System One) classifier vets each turn against a declarative policy and recommends the subagent model route, so routine work runs at flash rates while the main model keeps the har

by dshplugin-me

Find DSH plugins and security-scan them before install

by meliwanx

Secure DeepSeek Harness plugin for official WeCom, DingTalk, and Feishu/Lark CLIs

by LLYlab

A permanent DSH plugin that bundles a developer workbench, an in-session conversation tree, and a plugin manager: build and run an LVAL project, browse its code, and keep per-program version snapshots

AI SQL 权限校验拦截插件 — DeepSeek Harness 通用 AI 数据库权限管控插件。 拦截智能体（Agent）生成的越权 SQL：不静默改写、直接拒绝执行，并把结构化权限 原因返回给模型，让模型自主剔除越权字段、更换统计口径，或用自然语言向用户解释权限不足。 插件 ID：dsh-plugin-sql-security-validate 适用框架：DeepSeek Harness（Cordis） 适配版本：DSH >= 0.1.x（本仓库验证于 0.2.0-rc.1） 开源协议：MIT

by feely0208

Check the dependency tree for poisoning and risk surface: install-time execution scripts, overly broad version ranges, non-registry sources

by samirliu

Deterministic goal-completion gate for DSH: contract-first AC grammar, re-runs every verify command itself (zero model trust), binds verdicts to a tree digest, denies false completion on update_goal/u