DSH插件商店

Aegis

GanyuanRan

Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

dsh-research-report

PerryLink

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.

odai

orziz

AI agent 通用任务治理框架：对齐目标与事实，规划和调度能力，守住授权与风险边界，治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.

AgentDebugX

AgentDebugX

【EMNLP 2026 Demo】A debugging framework for agentic AI systems: diagnose failures, attribute root causes, recover with evidence, and validate fixes through reruns.

oh-my-knowledge

lizhiyao

OMK — Evidence-backed evaluation and observability for prompts, RAG, skills, agents, and workflows. Native Codex, Claude Code, and DeepSeek Harness support.

dsh-score

PerryLink

Multi-dimensional quality scoring for DeepSeek Harness plugins: scores a repo or npm package across install success (consuming dsh-test-drive results), maintenance activity, documentation completeness, security scan, and protocol compliance — every conclusion backed by real CLI evidence with audit timestamps.

dsh-self-evolving

timwhitez

Evidence-first, crash-resumable self-evolution engine for DeepSeek Harness and Harbor.

engineer-software

KirschBluteX

Evidence-driven engineering workflows for Codex and DeepSeek Harness, backed by deterministic routing and behavior evaluations.

smokinggun

morluto

Help your agents find the smoking gun they're looking for. Optimization evidence for agents: find complexity hotspots.

dsh-project-orchestrator

zhangz-2018

Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.

superself

fxylabs

The open Company State Runtime — version control for your project's state. Goals, decisions, work, and evidence outlive every chat, context window, and agent session. Ships the self CLI.

stalegreen

pavangupta352

Keeps a coding agent's green claims honest: verification runs are recorded unmasked, and done is blocked when the evidence is stale, failed or masked.

dsh-showcase

DoveLi-Gu

Local, verifiable delivery evidence reports and DSH plugin for coding-agent projects.

dsh-qa

ZSeven-W

DeepSeek Harness plugin that does QA: an agent explores your app like a real user and leaves evidence, then the explored path is exported as a deterministic replay scenario you run every release. Orchestrates the browser, macOS desktop, iOS and Android drivers — never a false green.

dsh-benchmark

dongsheng123132

Deterministic revision-pinned benchmarks and regression evidence for DeepSeek Harness

beforedone

rrrrrredy

Require fresh, file-bound verification evidence before coding agents declare completion.

governed-workflow-for-dsh

zcx369658780

Policy-enforced, evidence-first governed workflows for DeepSeek Harness agents.

fullstack-expert

heyadhithya

Cordis-native, evidence-driven full-stack engineering discipline for DeepSeek Harness agents

codex-skills

oukeming64-tech

Evidence-first agent skills for handoff auditing and documentation sync, packaged for Codex and DeepSeek Harness.

software-design-test

Inceptzws

DeepSeek Harness 插件：模拟真实用户做软件设计测试 / Simulate a real user to test software — personas, task cards, three input modes, screen evidence, zero input injection.

dsh-cordis-devtools

wang-kaopu

Give coding Agents runtime evidence for debugging and verifying DSH / Cordis plugins. 让 Coding Agent 获得用于调试和验证 DSH / Cordis 插件的运行时证据。