A skill for reading Google Docs, Sheets, Slides, and Drive files through the Google Workspace command-line tool, then turning their contents into clean Markdown text.

Find files in Google Drive, including Shared Drives, and read documents, spreadsheets, or presentations for use as project context.

It removes the need to copy content manually when an agent needs information from Google Workspace.

gws-reader — Skill for Claude Code by RDEL-Group

Install

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.

Any agent

npx skills add RDEL-Group/compound-knowledge-work --skill gws-reader

Clone the repo

git clone --depth 1 https://github.com/RDEL-Group/compound-knowledge-work

Made for: Claude Code.

Or install compound-knowledge-work, the plugin that ships this one along with the rest of its 5 skills, 7 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rdel-group/compound-knowledge-work/gws-reader/github.svg)](https://agentmods.dev/skills/rdel-group/compound-knowledge-work/gws-reader)

Your own site

<a href="https://agentmods.dev/skills/rdel-group/compound-knowledge-work/gws-reader"><img src="https://agentmods.dev/badge/skills/rdel-group/compound-knowledge-work/gws-reader/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rdel-group/compound-knowledge-work/gws-reader"><img src="https://agentmods.dev/badge/skills/rdel-group/compound-knowledge-work/gws-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,155 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.

Model	Per session	Once invoked
Fable 5.1	$0.00081	$0.02155
Opus 5.5	$0.00032	$0.00862
Sonnet 5.5	$0.00016	$0.00431
Haiku 4.5	$0.00008	$0.00215

Measured 1mo ago against content hash 46f4cb116746, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gws-reader 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 1mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/docs_to_markdown.py, scripts/sheets_to_markdown.py, scripts/slides_to_markdown.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/gws-reader/SKILL.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Workspace Reader

Read files from Google Drive and convert their content to clean markdown. Supports Google Docs, Sheets, and Slides. Searches across all Drives including Shared Drives.

When to Use

User asks to read, view, or fetch a Google Doc, Sheet, or Slides file
User asks to search or find files on Google Drive
/ckw:drive command needs to search or read files
/ckw:import-reference --from-drive needs to fetch content before importing
Any CKW agent needs Google Workspace content as context

Prerequisites

Check 1: gws CLI installed

which gws

If not found:

The Google Workspace CLI (gws) is required but isn't installed.

Install:
  npm install -g @googleworkspace/cli

Then authenticate:
  gws auth setup
  gws auth login

After setup, run this command again.

Stop here — do not attempt any operations without gws.

Check 2: Authentication valid

gws drive files list --params '{"pageSize": 1}' 2>&1

If the response contains "401" or "authError":

Your Google Workspace session has expired. Re-authenticate:
  gws auth login

Then try again.

Stop here — do not attempt operations with expired auth.

Mode: Search

Find files by name across all Drives (including Shared Drives).

Step 1: Execute search

gws drive files list --params '{"q": "name contains '\''SEARCH_TERM'\''", "includeItemsFromAllDrives": true, "supportsAllDrives": true, "corpora": "allDrives", "pageSize": 10, "fields": "files(id,name,mimeType,modifiedTime,parents)"}'

To search within a specific Shared Drive (if user specifies):

gws drive files list --params '{"q": "name contains '\''SEARCH_TERM'\''", "driveId": "DRIVE_ID", "includeItemsFromAllDrives": true, "supportsAllDrives": true, "corpora": "drive", "pageSize": 10, "fields": "files(id,name,mimeType,modifiedTime,parents)"}'

To list available Shared Drives:

gws drive drives list

Escaping apostrophes: if SEARCH_TERM contains an apostrophe, escape it as \' inside the query (e.g., O'Brien → O\'Brien) — otherwise the Drive q string terminates early and the search fails or returns wrong results.

Read the full file on GitHub · 242 lines

Files

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.

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.

1mo ago First seen · 242 lines · 81 tokens per session scan A 46f4cb116746

Subscribe to this mod's changes

gws-reader is a skill published in the GitHub repository RDEL-Group/compound-knowledge-work (9 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 2,155 once invoked, about $0.0003 per session on Opus 5.5. 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.

Claude Code Documents Spreadsheets claude-code-plugin compound-engineering knowledge-work

skill-doc-delivery

Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.

nyldn/claude-octopus · 29 tokens

add-excel

Adds Excel Online (Business) connector to a Power Apps code app. Use when reading or writing Excel workbook data from OneDrive or SharePoint.

microsoft/power-platform-skills · 33 tokens

analyze

Analyze a large file (CSV, Excel, PDF, JSON, code) and return a token-efficient summary. Instead of reading thousands of rows or pages, get schema + statistics + sample in under 500 tokens. Use when user mentions a file path, asks to analyze data, pastes many rows, or references a CSV/Excel/PDF/JSON file.

Shweta-Mishra-ai/tokenmizer · 76 tokens

brand-xlsx

Brand-aware Excel engine. Use to (1) EXTRACT a company's brand from a .xlsx template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE a new on-brand .xlsx from a GridDocument fill manifest. Trigger on "extract our brand", "use our workbook template"…

ferdinandobons/brand-docs · 141 tokens

gsheets

Google Sheets via MCP — read, write, create, list, share spreadsheets. Use when reading, writing, or managing Google Sheets data.

martineserios/thebrana · 31 tokens

strategy-decompose

Decompose a strategy handed down from above into a hierarchy of aspects and states, audit it for necessity, sufficiency and overlap, and output it as an xlsx. Use before writing your own team's or unit's policy from a company/department/team strategy, when the user wants to break a strategy down into "what state we…

atman-33/workhub · 85 tokens