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/fanfan-de/anybox/documentsnpx skills add fanfan-de/anybox --skill documentsgit clone --depth 1 https://github.com/fanfan-de/anyboxWrote 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/fanfan-de/anybox/documents)<a href="https://agentmods.dev/skills/fanfan-de/anybox/documents"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/documents.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 | $0.00061 | $0.07585 |
| Opus 5 | $0.00030 | $0.03793 |
| Sonnet 5 | $0.00012 | $0.01517 |
| Haiku 4.5 | $0.00006 | $0.00758 |
Grade A, and why
Word DOCX Builder 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 yesterday.
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.
This is a copy
92% identical to docx — 106 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Word DOCX Builder Skill (Read • Create • Edit • Redline • Comment)
Use this skill when you need to create or modify editable Microsoft Word .docx files in this container environment and verify them visually.
Tools + Contract
- Use Codex workspace dependencies for docx artifact work: resolve them through the workspace dependency loader or runtime skill, then treat the returned Node/Python runtimes and package directory as authoritative. Do not use system
node, systempython, global npm packages, or repo-local installs. - For document creation and deterministic OOXML edits, it is still acceptable to use the bundled Python/OOXML helper scripts in this skill package when the JS surface is incomplete.
- Run any builder or helper file from a writable workspace or temp directory, not from the managed dependency directory itself.
- Final user-facing responses should describe only the requested document result and link only to the final
.docxdeliverable unless the user explicitly asks for QA intermediates.
Non-negotiable: render → inspect PNGs → iterate
You do not “know” a DOCX is satisfactory until you’ve rendered it and visually inspected page images. DOCX text extraction (or reading XML) will miss layout defects: clipping, overlap, missing glyphs, broken tables, spacing drift, and header/footer issues.
Shipping gate: before delivering any DOCX, you must:
- Run
render_docx.pyto producepage-<N>.pngimages (optionally also a PDF with--emit_pdf) - Open the PNGs (100% zoom) and confirm every page is clean
- If anything looks off, fix the DOCX and re-render (repeat until flawless)
If rendering fails because LibreOffice/soffice is missing, it is acceptable to return the requested DOCX without rendered PNG QA. In that fallback case, use the relevant Markdown task docs in this skill package as the authoritative guidance for building and checking the document structurally, state clearly in the final response that rendering/visual QA could not be completed, and do not imply that the document passed the render gate.
What ships with it
60 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.
- agents/openai.yaml 322 B
- assets/file-document.png 11 KB
- examples/end_to_end_smoke_test.md 930 B
- LICENSE.txt 1.4 KB
- manifest.txt 1.9 KB
- ooxml/comments.md 1.8 KB
- ooxml/hyperlinks_and_fields.md 2.4 KB
- ooxml/rels_and_content_types.md 1.3 KB
- ooxml/tracked_changes.md 1.6 KB
- references/design_presets.md 16 KB
- references/header_templates.md 12 KB
- render_docx.py 14 KB runs code
- scripts/a11y_audit.py 13 KB runs code
- scripts/accept_tracked_changes.py 5.4 KB runs code
- scripts/add_tracked_replacements.py 5.7 KB runs code
- scripts/apply_template_styles.py 4.0 KB runs code
- scripts/captions_and_crossrefs.py 9.5 KB runs code
- scripts/comments_add.py 8.4 KB runs code
- scripts/comments_apply_patch.py 4.8 KB runs code
- scripts/comments_extract.py 5.3 KB runs code
- scripts/comments_strip.py 4.7 KB runs code
- scripts/content_controls.py 11 KB runs code
- scripts/docx_ooxml_patch.py 22 KB runs code
- scripts/docx_table_to_csv.py 2.1 KB runs code
- scripts/fields_materialize.py 10 KB runs code
- scripts/fields_report.py 5.6 KB runs code
- scripts/flatten_ref_fields.py 4.6 KB runs code
- scripts/footnotes_report.py 2.8 KB runs code
- scripts/heading_audit.py 3.2 KB runs code
- scripts/images_audit.py 5.7 KB runs code
- scripts/insert_note.py 8.8 KB runs code
- scripts/insert_ref_fields.py 6.9 KB runs code
- scripts/insert_toc.py 5.0 KB runs code
- scripts/internal_nav.py 12 KB runs code
- scripts/make_fixtures.py 8.5 KB runs code
- scripts/merge_docx_append.py 3.8 KB runs code
- scripts/privacy_scrub.py 5.5 KB runs code
- scripts/redact_docx.py 9.3 KB runs code
- scripts/render_and_diff.py 4.7 KB runs code
- scripts/section_audit.py 2.6 KB runs code
- scripts/set_protection.py 4.9 KB runs code
- scripts/style_lint.py 5.3 KB runs code
- scripts/style_normalize.py 5.5 KB runs code
- scripts/table_geometry.py 9.6 KB runs code
- scripts/watermark_add.py 5.2 KB runs code
- scripts/watermark_audit_remove.py 4.6 KB runs code
- scripts/xlsx_to_docx_table.py 5.5 KB runs code
- tasks/accessibility_a11y.md 1.9 KB
- tasks/captions_crossrefs.md 3.7 KB
- tasks/clean_tracked_changes.md 1.6 KB
- tasks/comments_manage.md 2.9 KB
- tasks/compare_diff.md 1.1 KB
- tasks/create_edit.md 1.7 KB
- tasks/fields_update.md 2.3 KB
- tasks/fixtures_edge_cases.md 1.7 KB
- tasks/footnotes_endnotes.md 1.8 KB
- tasks/forms_content_controls.md 2.0 KB
- tasks/headings_numbering.md 1.8 KB
- tasks/images_figures.md 1.3 KB
- tasks/multi_doc_merge.md 1.5 KB
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.
- yesterday First seen · 408 lines · 61 tokens per session scan A 019370cd4286
Word DOCX Builder is a skill published in the GitHub repository fanfan-de/anybox (58 stars, last pushed 22d ago), licensed MIT. It adds 61 tokens to every session and 7,585 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to docx, differing in 106 lines, and is treated as a copy.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
gog-slides
Google Slides operations through gog.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…