Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/fa-ce/historiographer-skills/docx-codenpx skills add Fa-ce/historiographer-skills --skill docx-codegit clone --depth 1 https://github.com/Fa-ce/historiographer-skillsWrote 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.
[](https://agentmods.dev/skills/fa-ce/historiographer-skills/docx-code)<a href="https://agentmods.dev/skills/fa-ce/historiographer-skills/docx-code"><img src="https://agentmods.dev/badge/skills/fa-ce/historiographer-skills/docx-code.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00127 | $0.01676 |
| Opus 5 | $0.00063 | $0.00838 |
| Sonnet 5 | $0.00025 | $0.00335 |
| Haiku 4.5 | $0.00013 | $0.00168 |
Grade A, and why
docx-code 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docx-code:依据代码生成格式统一的项目文档
适用场景
需要把一个软件项目(可含前端/后端/算法多个仓库)的真实功能整理成一份正式 Word 文档 (设计说明书、功能说明书等),且格式必须与一份已有的标准 .docx 模板严格一致时使用。
核心做法:复制模板 .docx,完整继承其样式定义,只重写正文,正文一律引用模板已有的固定样式—— 因此各级标题、正文、图、表的字体/字号/缩进/行距/编号都与模板完全统一,不自造任何样式。
引擎 scripts/docxgen.py 仅用 Python 标准库,无需 python-docx / pandoc / LibreOffice,
可在任意装有 Python 3 的系统直接运行。
前置条件
- 一份格式标准的参考 .docx 模板(提供全部样式与版式)。
- 待编写文档的源代码仓库。
- Python 3(标准库即可)。
工作流
1. 解析模板,摸清可用样式与层级范式
python scripts/inspect_template.py <模板.docx>
输出 docxgen 将使用的样式映射(各级标题 / 正文 / 题注 / 表格的 styleId、字体、字号)与模板现有大纲。 据此理解模板的层级范式(例如:功能模块[H1] → 各大模块[H2] → 设计模块[H3] → 模块功能组成[H4] → 子模块[H5]), 新文档应沿用同一层级模式。
2. 分析代码仓库,提炼功能模块树
基于真实代码(不臆测)梳理"一级功能模块 → 子功能":
- 前端:路由配置、菜单、
views目录结构、关键页面组件 → 功能模块与子功能划分 - 后端:Controller/API 分组、Service、领域实体/枚举 → 能力与端点
- 算法:模块目录、各算法实现 → 方法/算子清单
大型或多仓库项目用子代理并行分析(每个仓库一个 Explore/general 代理),统一要求输出:
## 一级模块:X 下逐条 - 子功能 — 一句话作用 [证据: 路径],并交叉印证。
若目标项目与模板属同类系统,模板中一致的功能模块结构可直接复用,差异集中在核心算法/业务模块。
3. 设计文档大纲
把功能模块树映射到模板层级(H1 总章 → H2 大模块 → H3 设计模块 → H4 功能组成 → H5 子模块)。 功能模块作为一级标题,具体功能归入其下。CRUD/导入导出类展开到子模块层;并列的算法/方法各占一节。
4. 用 docxgen 生成
把大纲与正文写成一个生成脚本(便于迭代重跑),顺序调用 b.h/b.p/b.table/b.image,最后 b.save():
import sys; sys.path.insert(0, 'scripts')
from docxgen import DocxBuilder
with DocxBuilder('模板.docx') as b: # 自动探测并继承模板样式
b.h(1, '功能模块')
b.p('本章描述各功能模块……')
b.h(2, '样本数据接入模块')
b.p('该模块负责……')
b.h(3, '文件接入模块'); b.h(4, '模块功能组成')
b.table(['序号', '格式', '说明'],
[['1', 'Excel', '按表头解析'], ['2', 'CSV', '文本表格']],
caption='支持的文件格式')
b.h(5, 'Excel文件导入子模块'); b.p('支持导入 .xlsx……')
# b.image('shots/login.png', caption='登录界面') # 需要配图时
print(b.save('输出.docx'))
5. 校验
save() 内置校验:XML 合法性 + 所有引用样式都存在于模板 + 返回结构统计
({'headings': {1:.., 2:..}, 'paragraphs': N, 'tables': M})。核对模块数与层级是否符合大纲。
可选版式预览(若已安装 LibreOffice,跨平台):
soffice --headless --convert-to pdf 输出.docx
关键约定
- 只用模板已有的固定样式(pStyle / tblStyle),不新增样式 → 全文格式天然统一。
- 标题多级编号(1 / 1.1 / 1.1.1 …)由模板标题样式自带(outlineLvl + 多级列表),不要手写编号。
- 图/表题注用
SEQ域自动连续编号;表题在表上方、图题在图下方(docxgen 已内置)。 - 正文/表格直接继承模板对应样式;表格附全框线、表头加粗+底纹、固定列宽。
- 内容描述基于真实代码,准确、信息密度高,避免空话套话。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 105 lines · 127 tokens per session scan A b099d582fe26
docx-code is a skill published in the GitHub repository Fa-ce/historiographer-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 127 tokens to every session and 1,676 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
pdf-verification-cli
Verify PDF page count and content using command-line tools when Python libraries unavailable.