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 CHENyiru3/AI-Skills-Collections --skill yiru-google-drivegit clone --depth 1 https://github.com/CHENyiru3/AI-Skills-CollectionsWrote 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/chenyiru3/ai-skills-collections/yiru-google-drive)<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/yiru-google-drive"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/yiru-google-drive/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/chenyiru3/ai-skills-collections/yiru-google-drive"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/yiru-google-drive.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 | $0.00048 | $0.00632 |
| Opus 5.5 | $0.00019 | $0.00253 |
| Sonnet 5.5 | $0.00010 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
yiru-google-drive 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configured Google Drive Transfers
The historical skill ID is retained; account, OAuth project, credentials, and storage locations belong in the operator's private configuration, not this skill. Reuse configured access. Use gws-shared for CLI mechanics and gws-drive for API operations. Diagnose authentication only when it fails; a transfer does not authorize changing credentials or sharing.
Files and destinations
Use supplied Drive IDs/resource keys and the requested local destination. Resolve ambiguous destinations before writing. Inspect an unfamiliar method's schema and the installed CLI version before relying on its flags.
gws drive +upload ./report.pdf --parent FOLDER_ID
gws drive files get --params '{"fileId":"FILE_ID","alt":"media"}' -o ./report.pdf
gws drive files export --params '{"fileId":"DOC_ID","mimeType":"application/pdf"}' -o ./document.pdf
Choose native-document export formats for the user's purpose. Do not treat a folder, shortcut, or Google-native document as an ordinary binary download. Where path validation requires it, use the actual source/destination directory as the working directory and paths beneath it; do not weaken path checks.
New uploads create items and may duplicate them on retry. Inspect an uncertain remote result before repeating it. Updating an existing item requires its ID and the requested overwrite scope.
Folder trees
Check whether the installed CLI provides the requested recursion. Otherwise use a task-scoped traversal with subprocess argument lists and JSON serialization.
- Upload: enumerate the requested tree, create folders including empty ones, and retain relative-path-to-Drive-ID mappings plus completed file IDs. Do not follow symlinks outside the requested tree implicitly.
- Download: list each folder with
'<ID>' in parents and trashed = false; requestnextPageTokenand follow it until absent. Recreate folders, download binaries, export native documents, and resolve shortcuts deliberately without cycles. Report unsupported or skipped entries. - Treat remote names as untrusted path components: reject absolute/traversal paths, resolve duplicate names with stable ID suffixes, and preserve existing local files unless replacement is requested.
- Check method-specific shared-drive options and local capacity. For a configured external storage mount, verify the intended mount is present and writable before creating destination directories.
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.
- yesterday First seen · 60 lines · 48 tokens per session scan A db65a3187503
yiru-google-drive is a skill published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 632 once invoked, about $0.0002 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 2026-11-13.
yiru-google-drive compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| yiru-google-driveCHENyiru3/AI-Skills-Collections | Skill | 2 | 3d ago | MIT | A | 48 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 108k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 36k | yesterday | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 50k | today | MIT | A | 48 | Claude Code |
| report-to-pdfasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 17 | Claude Code, Codex |
| legal-holdanthropics/claude-for-legal | Skill | 10k | today | Apache-2.0 | A | 68 | Claude Code |
| artifact-template-minimal-letterheadasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 54 | Claude Code, Codex |