code-ownership-audit
Decides whether Python code is original or a derivative work: reports the longest identical expression span against an upstream tree, an exemption rationale per finding, and a risk list. Pure stdlib `ast` analysis — offline, no model calls.
判定 Python 代码是原创还是演绎作品:给出与上游最长相同表达片段、逐条豁免依据和风险清单。纯标准库 `ast` 分析——离线运行,不调用模型。
How to install
dsh plugin add github:ffseika0304/code-ownership-audit git clone https://github.com/ffseika0304/code-ownership-audit ~/.claude/skills/code-ownership-audit About
你引入了一段开源代码,改了改,现在它算谁的? **法律上,"改过"不等于"是我的"。** 演绎作品(derivative work)仍受上游许可证约束。 **AI 大量生成代码后,这个问题变得更普遍。** 你可能根本不知道某段实现和上游有多像。 交付给甲方时,把演绎作品当自有资产声明,是实打实的风险。 这个工具做的事:把你的代码和上游逐个 AST 节点比,**告出最长的相同表达片段**,并对每条风险给出**豁免依据**(是通用惯用法?是接口约定必然形状?还是真的抄了表达)。 --- Highlights **🥇 纯 AST 静态分析,不联网、不调模型。** 审计引擎只用 Python 标准库 —— 你的代码不出本机,不存在隐私泄露。 **🥇 两种安装方式,同一套引擎。** Agent Skill 和 DSH Plugin 共享 audit.py,按你的 Agent 支持情况选。 **🥇 两档报告,预览免费不限次。** 免费档给出风险总数、类型分布、一句话摘要;完整档 ¥0.2/次,含行号、修复建议、服务器签名审计凭证。 **🥇 x402 协议付款。** 服务端是纯支付预言机:只验钱、签发回执,**不接收也不存储你的任何代码**。回执用内嵌公钥离线验签。 **🥇 31 项测试覆盖。** python -m pytest -q 一键跑完,全部通过再发版。 --- 国内加速 本…
Recommendation signals
Meta
- License
- MIT
- Language
- Python
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-09-07
- Created
- 2026-09-07
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- agent-skills, ast-analysis, claude-code, clean-room, code-audit, code-ownership, coding-agents, copyright, deepseek-harness, derivative-work, dsh, dsh-plugin, dsh-skill, license-compliance, plagiarism-detection, python, sbom, static-analysis, vibe-coding, x402
Related plugins
superpowers
obra/superpowers
An agentic skills framework & software development methodology that works.
mcp-server-chart
antvis/mcp-server-chart
🤖 A visualization mcp & skills contains 25+ visual charts using @antvis. Using for chart generation and data analysis.
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