software-copyright

software-copyright is a skill for Claude Code, Codex from ThomasMoreAI/legal-skills-open. It costs 95 tokens per session (6,571 once invoked), scanned A, original, Apache-2.0.

A guided workflow for preparing Chinese software copyright registration materials from a real software project. It produces drafts such as application details, source-code documents, and a user manual.

In plain words
What is it for?
Use it to analyze a project, select representative source files, prepare software copyright application content, and create Word or text materials.
Why use it?
It turns a codebase into traceable registration paperwork without inventing code or software features.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/confirm_stage.py --workdir 软件著作权申请资料 --stage <阶段名> --note "<用户确认内容>".

Good fit Use it to analyze a project, select representative source files, prepare software copyright application content, and create Word or text materials.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-open
agentmods
npx agentmods add skills/thomasmoreai/legal-skills-open/software-copyright

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for software-copyright

README.md
[![agentmods](https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/software-copyright/github.svg)](https://agentmods.dev/skills/thomasmoreai/legal-skills-open/software-copyright)
Your own site
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/software-copyright"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/software-copyright/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for software-copyright

Your own site · 80×15
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/software-copyright"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/software-copyright.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00095 $0.06571
Opus 5 $0.00048 $0.03285
Sonnet 5 $0.00019 $0.01314
Haiku 4.5 $0.00010 $0.00657

Measured 8d ago against content hash 3172e4dc3ffd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

software-copyright scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

cn/ip/skills/software-copyright/SKILL.md · 452 lines

How it starts

The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.

软著申请资料生成

这个 skill 生成可审阅、可追溯的软著申请资料。核心原则:

  • 固定输出目录:当前工作目录下的 软件著作权申请资料/。不要默认写到 /tmp/private/tmp 或其他临时目录。
  • 只有测试 skill 自身时才允许显式指定临时目录;面向用户生成材料时必须写入当前目录。
  • 先生成 Markdown 草稿,用户确认后再生成正式 Word/TXT。
  • 正式 Word/TXT 只能写入 软件著作权申请资料/正式资料/,不要散落在输出目录根部。
  • 正式 Word/TXT 的文字一律使用默认黑色字体,不生成蓝色超链接、主题色标题或其他彩色文字;Markdown 链接写入 Word 时必须转成普通文本。
  • 正式资料中的软件名称必须与 草稿/申请表信息.md 的“软件全称”字段一致;正式生成时以已确认的申请表软件全称为准。
  • 正式代码 Word 页眉中的版本号必须与 草稿/申请表信息.md 的“版本号”字段一致;正式生成时以已确认的申请表版本号为准。
  • 代码材料必须来自真实项目源码,禁止 AI 编造代码。
  • 写申请表和操作手册前,必须先形成模型研判后的 草稿/业务理解.md/json,理解软件业务、行业、目标用户、核心价值和操作流程。
  • 脚本只能收集项目证据、校验字段和生成文件;行业判断、功能抽取、代码抽取选择、操作手册结构必须由模型阅读项目后决定,不得依赖脚本关键字表或固定范本。
  • 优先抽取前端代码:入口、路由、页面、核心组件、接口封装、状态管理、工具函数。
  • 生成代码材料前,必须先生成代码文件候选清单;模型理解项目后填写抽取文件、行段和选择理由,再让用户确认或修改。
  • 代码优先抽取模型和用户确认的、最能体现软件真实功能和运行逻辑的源码;不足 60 页时,从其他相关源码文件补充到 60 页;候选源码仍不足 60 页时,才生成全部代码文档。
  • 操作手册面向审核员,用通用语言说明软件用途和操作流程。
  • 操作手册草稿必须按章节写成通顺段落,不能只给功能列表;每个核心模块都要用普通人能看懂的语言说明模块用途、操作过程和结果反馈。避免代码、框架、接口、状态管理、异步任务等技术化表达;撰写过程中由 agent 自行循环检查、扩写和修正,完整草稿完成后只向用户发起一次整体确认。
  • 操作手册必须去除明显“AI 味”:避免空泛赞美、营销口号、万能句式、每章同一结构、过度对称的排比、没有项目细节的正确废话、频繁使用“旨在、赋能、一站式、智能化、高效便捷、显著提升、强大能力、丰富功能”等套话。每段都应能回答“这个项目里这个功能具体做什么、用户看见什么、操作后有什么结果”。
  • 操作手册生成必须同步输出 草稿/操作手册自检记录.md草稿/操作手册自检记录.json,记录初稿、按项目流程扩写、去制式表达等自检轮次;如果前 3 轮仍发现问题,必须继续补写修正,直到问题清零或记录无法自动修复的原因后再停止。
  • 截图方式必须先让用户选择:Chrome DevTools MCP、Codex Computer Use、用户自行截图。用户选完后,再检查当前 MCP / Computer Use 能力是否可用;如果用户说现在不截图、先跳过截图或截图失败,操作手册仍必须保留清晰可见的截图预留位置,正式 Word 中也要能看到。
  • 申请表信息中的硬件/系统环境必须让用户确认或填写,不能硬编码。
  • Word 生成能力必须使用本 skill 内置的 vendor/docx-toolkit;不得引用外部 DOCX 目录。

强制人工门禁

凡是涉及用户选择、确认或补充信息的阶段,必须先停止当前执行,不得继续调用下一步脚本。即使处于自动审核、自动继续或无人值守模式,也必须把 STOP_FOR_USERNEXT_ACTION 原样告知用户,并等待用户输入后再继续。

禁止使用“用户未选择则默认继续”的逻辑。用户回复确认后,先用确认脚本记录对应门禁,再进入下一阶段:

python3 scripts/confirm_stage.py --workdir 软件著作权申请资料 --stage <阶段名> --note "<用户确认内容>"

必须停住的门禁:

  • environment:完整 DOCX 环境缺失时,用户必须选择“安装完整环境”或“使用基础 DOCX 兜底继续”。
  • project:存在多个项目候选目录时,用户必须指定项目目录。
  • business草稿/业务理解.md 生成后,用户必须确认行业、目标用户、核心功能和申请口径。
  • application-fields草稿/申请表信息.md 生成后,用户必须补全并确认硬件、系统环境、著作权人、日期等字段。
  • code-selection草稿/代码文件选择.json 生成后,用户必须确认或修改抽取文件和行段。
  • screenshot-method:操作手册截图前,用户必须在 Chrome DevTools MCP、Codex Computer Use、用户自行截图三种方式中选择一种;如果用户明确说“现在不截图/先跳过截图”,记录为 skip
  • markdown:全部 Markdown 草稿完成后,用户必须确认可以进入 Word/TXT 生成。

Read the full file on GitHub · 452 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 452 lines · 95 tokens per session scan A 3172e4dc3ffd

Subscribe to this mod's changes

software-copyright is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (72 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 95 tokens to every session and 6,571 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.