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 skills add fanfan-de/anybox --skill google-docsgit 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/google-docs)<a href="https://agentmods.dev/skills/fanfan-de/anybox/google-docs"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/google-docs/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.
<a href="https://agentmods.dev/skills/fanfan-de/anybox/google-docs"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/google-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.04108 |
| Opus 5 | $0.00035 | $0.02054 |
| Sonnet 5 | $0.00014 | $0.00822 |
| Haiku 4.5 | $0.00007 | $0.00411 |
Grade A, and why
google-docs 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 9d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Docs
Use this skill for Google Docs work in Codex local-plugin sessions.
For blank or basic native Google Docs, create the doc directly with the Google Drive connector. Use [@documents](plugin://documents@openai-primary-runtime) plus DOCX import only when the requested deliverable needs polished document authoring, complex layout, visual design, image/figure placement, page-level QA, branded styling, or export-quality fidelity.
Purpose Of This File
This file is intentionally minimal and covers:
- connector loading and runtime boundaries in the Codex local-plugin environment
- the direct native-create route for blank and basic Google Docs
- the DOCX-first native import route for polished or complex Google Docs
- the direct-request workflow for existing and newly created Google Docs
- stateful operation and mandatory routing to reference files
All formatting, citation, table, request-shape, and production rules live in references/.
Read only the references required for the task. For the common calendar-backed meeting-notes edit, references/reference-meeting-notes-direct.md is the single task reference unless the task adds tables, figures, citations, import/export, or other non-meeting-notes requirements.
Default Routing
Use this routing:
- Blank or basic native Google Docs creation: read
references/reference-native-create-direct.md, callmcp__codex_apps__google_drive._create_filewithmime_type: "application/vnd.google-apps.document", and use direct DocsbatchUpdaterequests only if content is requested. - Polished or complex net-new Google Docs creation: use
[@documents](plugin://documents@openai-primary-runtime)to create a local.docxfirst, explicitly selecting thegoogle_docs_defaultdesign preset unless the user asked for a special, branded, or highly polished visual treatment. Then readreferences/reference-import-docx-to-native-docs.mdand import withmcp__codex_apps__google_drive_import_documentusingupload_mode: "native_google_docs". - If the Documents plugin is unavailable for a polished or complex deliverable, report that the required local Documents authoring path is unavailable. Do not block blank or basic native Google Doc creation on the Documents plugin.
- Existing Google Docs reads, summaries, edits, comments, and template-preserving modifications: use Google Docs connector or app tools directly.
What ships with it
18 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 415 B
- assets/google-docs-small.svg 2.1 KB
- assets/google-docs.png 64 KB
- references/reference-citations-and-hyperlinks.md 2.0 KB
- references/reference-connector-runtime-and-safety.md 8.2 KB
- references/reference-direct-request-composition.md 7.6 KB
- references/reference-figures-and-image-insertion.md 3.4 KB
- references/reference-foreground-guard.md 2.5 KB
- references/reference-headings-and-question-format.md 5.4 KB
- references/reference-import-docx-to-native-docs.md 5.7 KB
- references/reference-meeting-notes-direct.md 8.8 KB
- references/reference-native-create-direct.md 4.1 KB
- references/reference-pdf-export-visual-qa.md 4.0 KB
- references/reference-request-shapes-and-write-safety.md 12 KB
- references/reference-response-and-list-format.md 1.8 KB
- references/reference-section-completeness-and-final-pass.md 8.0 KB
- references/reference-smart-chips-and-building-blocks.md 5.0 KB
- references/reference-table-formatting-deep-dive.md 9.7 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.
- 9d ago First seen · 203 lines · 70 tokens per session scan A 69cf5d43a24e
google-docs is a skill published in the GitHub repository fanfan-de/anybox (57 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 4,108 once invoked, about $0.0003 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.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.