mcp-google-drive: Skill for Claude Code

.claude/skills/gdrive/SKILL.md

gdrive is a skill for Claude Code from abanka27/mcp-google-drive. It costs 72 tokens per session (783 once invoked), scanned A, original, MIT.

A command-line tool for reading and writing Google Drive files, Docs, and Sheets. It can also inspect document headings, sections, and comments.

In plain words
What is it for?
Searching Drive, reading selected document sections, viewing outlines or comments, and creating or updating Google Docs from Markdown.
Why use it?
It lets an agent work with Google documents from the terminal instead of manually copying their contents.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is abanka27/mcp-google-drive's own configuration. It tells Claude Code how to work on mcp-google-drive itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-google-drive configures →

Reuse

Borrowing it

Nothing to install: this file belongs to abanka27/mcp-google-drive. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/abanka27/mcp-google-drive/master/.claude/skills/gdrive/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/abanka27/mcp-google-drive

Made for: Claude Code.

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 gdrive

README.md
[![agentmods](https://agentmods.dev/badge/skills/abanka27/mcp-google-drive/gdrive/github.svg)](https://agentmods.dev/skills/abanka27/mcp-google-drive/gdrive)
Your own site
<a href="https://agentmods.dev/skills/abanka27/mcp-google-drive/gdrive"><img src="https://agentmods.dev/badge/skills/abanka27/mcp-google-drive/gdrive/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 gdrive

Your own site · 80×15
<a href="https://agentmods.dev/skills/abanka27/mcp-google-drive/gdrive"><img src="https://agentmods.dev/badge/skills/abanka27/mcp-google-drive/gdrive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 783 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 $0.00072 $0.00783
Opus 5 $0.00036 $0.00392
Sonnet 5 $0.00014 $0.00157
Haiku 4.5 $0.00007 $0.00078

Measured 9d ago against content hash 54610508ef05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gdrive 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.

.claude/skills/gdrive/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Drive CLI (gdrive)

gdrive reads and writes Google Drive/Docs/Sheets from the shell. Every command takes a Drive file ID or a Google URL. Content goes to stdout (pipe or redirect it); pass --json for structured output.

Token-saving rule: never paste a large doc inline. Redirect to a file and read it with pagination:

gdrive docs read <id|url> > /tmp/doc.md      # then Read /tmp/doc.md with offset/limit
gdrive docs read <id|url> --section "Heading" # or just one section
gdrive docs headings <id|url>                 # list sections first

Is it set up?

If gdrive is "command not found" or a command fails with an auth error, it isn't configured yet. Tell the user to run, inside the mcp-google-drive repo:

npm run setup       # builds, places Google credentials, signs in, links gdrive onto PATH

npm run setup prints exact next steps (with links) if Google credentials are missing — it's a ~2-minute one-time GCP step. Do not try to work around setup.

Commands

gdrive search <query> [--type docs|sheets] [--page-size N]   # find files -> JSON
gdrive meta <id|url>                                         # file metadata
gdrive docs read <id|url> [--section "H"] [--json] [--no-images]
gdrive docs headings <id|url> [--min N] [--max N]            # outline
gdrive docs comments <id|url> [--include-resolved]           # comments + replies
gdrive docs create --name "Title" [--from FILE]              # new Doc from Markdown (stdin ok)
gdrive docs update <id|url> [--from FILE]                    # full-replace Doc from Markdown
gdrive sheets read <id|url> [--range "'Tab'!A1:D"] [--csv|--tsv|--json]
gdrive files read <id|url>                                   # raw bytes/text

Patterns

  • Find then read: gdrive search "spec" --type docs, take the id, then gdrive docs read <id> > /tmp/spec.md.
  • Sheet data into tools: gdrive sheets read <id> --range "'Sheet1'!A:D" --csv | ....
  • Review feedback: gdrive docs comments <id> (author, quoted text, replies).
  • Write a doc: author Markdown locally, then gdrive docs create --name "Notes" --from notes.md (prints the new URL), or echo "# Hi" | gdrive docs update <id> to replace an existing doc's body.

Read the full file on GitHub · 64 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. 9d ago First seen · 64 lines · 72 tokens per session scan A 54610508ef05

Subscribe to this mod's changes

gdrive is a skill published in the GitHub repository abanka27/mcp-google-drive (1 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 783 once invoked, about $0.0004 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.