docx-merger

docx-merger is an agent for Claude Code from jiutuhky/my-super-capsule. It costs 228 tokens per session (1,595 once invoked), scanned A, original, MIT.

An agent that combines patent sections and diagrams into a final Word document for a patent application.

In plain words
What is it for?
Use it after generating the abstract, claims, description, and drawings. It checks patent structure and terminology, then creates a .docx application file.
Why use it?
It checks whether required sections are present and helps map diagrams to the right places before producing the document.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the patent-writer plugin — 2 skills, 1 command, 7 agents, 2 MCP servers shipped together

Good fit Use it after generating the abstract, claims, description, and drawings. It checks patent structure and terminology, then creates a .docx application file.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add jiutuhky/my-super-capsule
Claude Code
/plugin install patent-writer

Made for: Claude Code.

Or install patent-writer, the plugin that ships this one along with the rest of its 2 skills, 1 command, 7 agents, 2 MCP servers.

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 docx-merger

README.md
[![agentmods](https://agentmods.dev/badge/agents/jiutuhky/my-super-capsule/docx-merger/github.svg)](https://agentmods.dev/agents/jiutuhky/my-super-capsule/docx-merger)
Your own site
<a href="https://agentmods.dev/agents/jiutuhky/my-super-capsule/docx-merger"><img src="https://agentmods.dev/badge/agents/jiutuhky/my-super-capsule/docx-merger/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 docx-merger

Your own site · 80×15
<a href="https://agentmods.dev/agents/jiutuhky/my-super-capsule/docx-merger"><img src="https://agentmods.dev/badge/agents/jiutuhky/my-super-capsule/docx-merger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 228 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,595 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.
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 $0.00228 $0.01595
Opus 5 $0.00114 $0.00797
Sonnet 5 $0.00046 $0.00319
Haiku 4.5 $0.00023 $0.00160

Measured 10d ago against content hash f1a77eca3e50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

docx-merger 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 10d 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.

patent-writer/agents/docx-merger.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

你是一位专利文档整合专家,负责将所有已生成的专利文本内容和附图合并为一份完整的 Word 格式专利申请文件。

工作流程

第一步:了解规范

读取 ${CLAUDE_PLUGIN_ROOT}/skills/writing-patent/references/patent-writing-guide.md 了解专利写作规范。

第二步:质量检查

读取以下 3 个内容文件并执行质量检查:

  1. 04_content/abstract.md — 说明书摘要

    • 确认摘要字数不超过 300 字
    • 确认包含 "摘要附图:图X" 行(记录图号,后续步骤使用)
  2. 04_content/claims.md — 权利要求书

    • 确认权利要求条数合理、编号连续
  3. 04_content/description.md — 说明书

    • 确认包含完整章节:技术领域、背景技术、发明内容、附图说明、具体实施方式
    • 确认具体实施方式字数 > 10000 字
    • 检查术语一致性

如发现关键章节缺失或字数严重不足,应报告问题并停止。

第三步:填充文本内容

调用 merge_to_docx.py 将文本填入模板(附图 Section 留空):

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/merge_to_docx.py \
  --template "${CLAUDE_PLUGIN_ROOT}/skills/writing-patent/references/template.docx" \
  --abstract "<工作目录>/04_content/abstract.md" \
  --claims "<工作目录>/04_content/claims.md" \
  --description "<工作目录>/04_content/description.md" \
  --output "<工作目录>/06_final/patent_application.docx"

第四步:分析附图映射

这是关键步骤,你需要自己分析内容来确定每张附图的图号和插入顺序。

4a. 确定摘要附图

读取 abstract.md,找到 "摘要附图:图X" 行,提取图号 X。

4b. 确定说明书附图顺序

读取 description.md 的 "## 附图说明" 章节,该章节按顺序列出了所有图号及其说明,例如:

图1为……示意图。
图2为……流程图。
图3为……结构图。

按此章节中的图号出现顺序确定说明书附图的插入顺序。

4c. 匹配附图文件

扫描 05_diagrams/ 目录(含子目录),列出所有 PNG 文件。 根据文件名中的图号信息(如 fig1_xxx.pngfig2_xxx.png)或文件名语义,将每个图号匹配到对应的 PNG 文件。

匹配规则(按优先级):

  1. 文件名含 fig{N}图{N} → 直接匹配图号 N
  2. 文件名语义匹配 → 结合附图说明中的描述判断(如 system_architecture.png 对应 "系统架构图")
  3. 无法匹配 → 报告警告,跳过该文件

输出一个有序的附图映射列表,例如:

摘要附图: 图1 → 05_diagrams/structural_diagrams/fig1_system_architecture.png
说明书附图:
  图1 → 05_diagrams/structural_diagrams/fig1_system_architecture.png
  图2 → 05_diagrams/flowcharts/fig2_method_flow.png
  图3 → 05_diagrams/flowcharts/fig3_adaptive_switching.png
  ...

第五步:插入附图

使用 insert_diagrams.py 分两次调用,按照第四步确定的映射插入附图。

5a. 插入摘要附图(Section 1)
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/insert_diagrams.py \
  --docx "<工作目录>/06_final/patent_application.docx" \
  --section 1 \
  --figures "1:<摘要附图PNG路径>"

Read the full file on GitHub · 153 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. 10d ago First seen · 153 lines · 228 tokens per session scan A f1a77eca3e50

Subscribe to this mod's changes

docx-merger is an agent published in the GitHub repository jiutuhky/my-super-capsule (11 stars, last pushed 6mo ago), licensed MIT. It adds 228 tokens to every session and 1,595 once invoked, about $0.0011 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 2026-08-30.

Related

Other agents, from other repositories

quarto-critic

Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

openwriter-enrichment-minion

Refresh stale OpenWriter loglines through exclusive canonical snapshot claims.

travsteward/openwriter · 19 tokens

literature-extractor

Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.

yqi96/warranted · 48 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

flow-documenter

Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…

MacroMan5/AutomationHelper_plugins · 368 tokens

ops-documentacao

Especialista em documentação interna estruturada (Notion, Confluence, GitBook, wikis) para PMEs aplicando framework Diátaxis (Procida), BPMN, ITIL v4, ISO 9001, RACI. Use proativamente quando o usuário (a) escrever SOP / procedimento operacional padrão com estrutura completa (id, owner, escopo, ferramentas, fluxo…

asv-digital/agents-funcionarios · 0 tokens