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 MattModeCode/claude-skills --skill gdrive-bulk-downloadgit clone --depth 1 https://github.com/MattModeCode/claude-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/mattmodecode/claude-skills/gdrive-bulk-download)<a href="https://agentmods.dev/skills/mattmodecode/claude-skills/gdrive-bulk-download"><img src="https://agentmods.dev/badge/skills/mattmodecode/claude-skills/gdrive-bulk-download/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/mattmodecode/claude-skills/gdrive-bulk-download"><img src="https://agentmods.dev/badge/skills/mattmodecode/claude-skills/gdrive-bulk-download.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00179 | $0.01337 |
| Opus 5 | $0.00089 | $0.00668 |
| Sonnet 5 | $0.00036 | $0.00267 |
| Haiku 4.5 | $0.00018 | $0.00134 |
Grade A, and why
gdrive-bulk-download scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gdrive-bulk-download
Bulk-download Google Docs, Google Slides decks, and existing PDF/DOCX/PPTX
files stored in Google Drive, using gstack's headless browser ($B) so it
works with restricted/managed accounts that can't install Claude's
Drive connector or browser extensions.
Inputs
- A list of URLs, either pasted directly in the prompt (one per line, in
any order, surrounding text ignored) or referenced as a file path
(one URL per line; blank lines and
#-comments ignored). - Optional output directory argument. Defaults to
~/Downloads.
Procedure
1. Collect URLs
Parse every https://docs.google.com/... or https://drive.google.com/...
URL out of the prompt text, or read them from the referenced file (one per
line, skip blank lines and lines starting with #).
2. Verify authentication
B=~/.claude/skills/gstack/browse/dist/browse
$B goto https://drive.google.com
$B text
Check the page text/title for signs of a logged-in session (account name, "My Drive", etc.) rather than a Google sign-in form. If not authenticated:
- Run
$B connectthen$B goto https://drive.google.comand$B handoff "log into the restricted Google account"so the user can complete login/MFA manually, then$B resume. /setup-browser-cookiesis generally unreliable for restricted/managed accounts — observed failure mode: Google auth cookies (SID,HSID,SAPISID, etc.) get scoped to a country-TLD domain (e.g..google.ca) that doesn't carry over todrive.google.com/docs.google.com. Prefer/connect-chrome+ manual login for these accounts; only suggest cookie import for accounts known to work with it.
Do not proceed to downloads until an authenticated session is confirmed.
3. Classify and resolve each URL
For each input URL, extract the file ID (the segment after /d/) and
resolve a download URL:
| Pattern | Resolved type | Download URL |
|---|---|---|
docs.google.com/document/d/{ID} |
Google Doc | https://docs.google.com/document/d/{ID}/export?format=pdf |
docs.google.com/presentation/d/{ID} |
Google Slides | https://docs.google.com/presentation/d/{ID}/export/pdf |
docs.google.com/spreadsheets/d/{ID} |
Google Sheet | unsupported — skip, record in manifest, do not download |
drive.google.com/file/d/{ID} (or open?id={ID}) |
Drive file (PDF/DOCX/PPTX) | https://drive.google.com/uc?export=download&id={ID} |
Any other direct .pdf/.docx/.pptx URL |
Direct file | use as-is |
What ships with it
1 file 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.
- 11d ago First seen · 128 lines · 179 tokens per session scan A 4f4ae0a04902
gdrive-bulk-download is a skill published in the GitHub repository MattModeCode/claude-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 179 tokens to every session and 1,337 once invoked, about $0.0009 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
baoyu-url-to-markdown
Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.
daily-report-generator
Automatically generate daily construction reports from field data, worker inputs, weather, and progress photos. Creates professional PDF reports.
payment-application-processor
Process construction payment applications. Validate schedule of values, calculate retainage, track billing status, and generate G702/G703 forms.
dgn-to-excel
Convert DGN files (v7-v8) to Excel databases. Extract elements, levels, and properties from infrastructure CAD files.
dwg-to-excel
Convert AutoCAD DWG files (1983-2026) to Excel databases using DwgExporter CLI. Extract layers, blocks, attributes, and geometry data without Autodesk licenses.
ifc-to-excel
Convert IFC files (2x3, 4x1, 4x3) to Excel databases using IfcExporter CLI. Extract BIM data, properties, and geometry without proprietary software.