logicprobe

DeepSeek HarnessClaude CodeCodex Skills Low risk

Claim-verification skill that checks design documents and plans against codebase facts, escalating behavioral claims to executable logic-primitive verification with structural checks and adversarial probes.

声称核查技能：将设计文档与计划中的每条声称对照代码库事实核验，行为类声称升级为可执行模型验证（结构检查与对抗探针）。

How to install

DeepSeek Harness dsh plugin add dsh-logicprobe

Claude Code git clone https://github.com/AmethystLuna/logicprobe ~/.claude/skills/logicprobe

Codex npx -y dsh-logicprobe

About

逻辑探针 (Logic Probe) 文档不是事实——代码才是。一个声称核查技能：逐条核验设计文档、架构规格、重构计划中每一个可验证的声称与代码库实际是否一致；遇到行为类声称时升级为可执行模型验证。 **跨平台** — 支持 Claude Code、Codex CLI、Cursor、Kimi CLI、OpenCode、ZCode。基于 Agent Skills 开放标准构建。功能 | 阶段 | 内容 | |------|------| | Phase 1-2 | 枚举每个可验证声称（API 名、文件路径、枚举值、数量、机制可行性）→ 逐条对照代码库给出证据 | | Phase 2a | 对提取的状态机模型执行 **7 项结构检查**：可达性、死锁、活性、确定性、事件/守卫完备性、不变量有效性 | | Phase 2b | **7 种对抗探针**：意外事件、竞态交错、顺序置换、配对对称（lock/unlock）、边界轰炸、资源注入、最小反例 | | 重构模式 | 前后模型对比——行为保持、不变量连续性、死锁回归、复杂度声称 | | 输出 | 结构化发现：精确 file:line 证据、严重性分级、修正方向——绝不在核查中直接改代码 | 模型永远先以转换表形式展示并**经用户确认后才运行**——模型提取错误是验证的头号失败模式。安装 Marketplace 安装（推荐）在 ~/.…

GitHub ↗

Recommendation signals

51 Tool quality · Based on stars, downloads, maintenance, security and docs

– User interest · Adjusted by in-site views, install copies and download clicks

51 Overall

0views

0unique visitors

0install copies

0download clicks

0outbound clicks

Links

GitHub ↗ npm ↗ Homepage ↗ Report issue ↗

Basic safety check

Findings: None
Sources: curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics: agent-plugin, agent-skills, ai-agents, claude-code, codex, cordis, deepseek-harness, dsh-plugin, verification

Related plugins

Claude Code New

Score92

superpowers

obra/superpowers

An agentic skills framework & software development methodology that works.

☆ 277.1K ↓ 1.3K Skills ↗

MCP Server New

Score88

mcp-server-chart

antvis/mcp-server-chart

🤖 A visualization mcp & skills contains 25+ visual charts using @antvis. Using for chart generation and data analysis.

☆ 4.3K ↓ 31.2K Skills ↗

Claude CodeDeepSeek HarnessCodexMCP Server New

Score80

ruflo

ruvnet/claude-flow

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

☆ 69.3K ↓ 79.5K Skills ↗

Claude Code New

Score77

caveman

JuliusBrussee/caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

☆ 100.7K ↓ – Skills ↗