DSH插件商店

J-Space-Cognition-Suite

Tiger3807861189

J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.

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.

embedded-workbench

AmethystLuna

Embedded C/C++ AI engineering plugin — firmware skills (FreeRTOS, Keil, HardFault, state machines) + 1% Rule / Plan Verification Gate discipline | 嵌入式 C/C++ 工程 AI 插件:固件技能与 agent 纪律。 For Claude Code, Codex, Cursor, Kimi, OpenCode, ZCode and DeepSeek Harness (dsh)

TaskBelay

Innocent-children

Task control for AI coding agents: explicit scope, bounded verification, durable state, safe recovery. Codex · Claude Code · DeepSeek · ZCode.

veripower

chipweaver

An open-source agent flow from natural language spec through Verilog RTL and UVM verification to front-end signoff on commercial EDA tools

anchorlaw

unknowbug

Code verification protocol for vibe coding — every claim must have a verifiable practice anchor.

dsh-plugin-doctor

zoahdev

Health checks for DeepSeek Harness plugins: manifest, patch, entry, build, pack, fresh-profile install verification — CLI + agent-callable plugin_check tool (RFC #1629 dsh plugin check).

dsh-verification-receipt

030611

Privacy-minimal heuristic per-turn verification summaries for DeepSeek Harness

logicprobe

AmethystLuna

AI 编程助手声明核查插件：状态机、协议、数据模型与并发声称的可执行逻辑原语验证（代价、概率、期限、组合、UML 审查、前后回归、导出），含 dsh 原生工具与 Agent Skills。 | Claim verification for AI coding agents — executable logic-primitive checks for state machines, data models and concurrency: cost, probability, deadlines, composition, UML review, before/after regression, export. Native dsh tools + Agent Skills.

dsh-plugin-doctor

PerryLink

Zero-dependency verification standard for DeepSeek Harness (dsh) plugins — static structure gates (R), cordis contract checks (K), sandbox smoke (D), ecosystem-listing checks (CC). 零依赖 DSH 插件核验标准：静态结构门禁、cordis 契约扫描、无头沙箱冒烟与生态收录核验。

behavior-enhancer-generic

Zoria-Lind

Behavior discipline for coding agents: read-before-write enforcement, failure convergence, write verification with auto-rollback, and a high-risk command gate. Ships FULL plugin/hook adapters for DSH, Claude Code, Codex, and Pi, plus a host-agnostic SOFT skill with ADAPTIVE adapter guidance.

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-plugin-anything

rootkiller6788

An agent-native compilation & verification pipeline that converts software capabilities such as CLI, APIs, and local services into installable, testable, verifiable DeepSeek Harness plugins.

dsh-llm-verifier

Web0926

DeepSeek Harness plugin that validates and ranks 3/5 independent coding-agent patches before approval-gated apply.

dsh-verify

263311487-ux

The quality gate for agent-built web apps. Real-browser acceptance checks — CLI, MCP (Claude Code / Cursor / Copilot), GitHub Action. Agents self-test and pass; real browsers tell the truth.

formalswarm

fashionmascherine-svg

Multi-agent validation for any repository: independent theses, adversarial critics, and a seal whose verdict is computed from real command exit codes — never from an agent's prose. One body, three runtimes: DeepSeek Harness, Claude Code, ZCode.

beforedone

rrrrrredy

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

butler-git

Hercules-debug

把「我改完了」变成可验证的事实:Δ(预期改动)+ P(检测程序)全过才产生 commit。零依赖,只用 node 和 git。 | Turn 'done' into a verifiable fact — a commit exists only if Δ + P both pass.

fullstack-expert

heyadhithya

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