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 agentmods add skills/openclaw/gogcli/gog-drivenpx skills add openclaw/gogcli --skill gog-drivegit clone --depth 1 https://github.com/openclaw/gogcliWhat 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 | $0.00010 | $0.00595 |
| Opus 5 | $0.00005 | $0.00298 |
| Sonnet 5 | $0.00002 | $0.00119 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
gog-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 today.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Drive
Use gog for Google Drive operations. Read ../gog/SKILL.md first for shared auth,
output, safety, and live-write rules.
Safe start
gog auth list --check --json --no-input
gog schema drive --json
gog --readonly --account [email protected] drive ls --max 20 --json --wrap-untrusted
- Select the account explicitly with
--account. - Use
--json --wrap-untrustedfor agent-readable Google content. - Use
--readonlywhen the task must not mutate Google data. - Use
--no-inputin automation and--dry-runbefore supported writes. - Confirm the exact account, object, and mutation before any write or delete.
Commands
| Command | Purpose |
|---|---|
activity |
Query Drive Activity audit events |
audit |
Audit Drive sharing without mutation |
bulk |
Bulk Drive permission operations |
changes |
Track Drive changes for sync and automation |
comments |
Manage comments on files |
copy |
Copy a file |
delete |
Move a file to trash (use --permanent to delete forever) |
download |
Download a file (exports Google Docs formats) |
drives |
List shared drives (Team Drives) |
du |
Summarize Drive folder sizes |
get |
Get file metadata |
inventory |
Export a read-only Drive inventory |
labels |
Read and modify Drive labels |
ls |
List files in a folder (default: root) |
mkdir |
Create a folder |
move |
Move a file to a different folder |
permissions |
List permissions on a file |
raw |
Dump raw Google Drive API response as JSON (Files.Get; lossless; for scripting and LLM consumption) |
rename |
Rename a file or folder |
revisions |
List and inspect file revisions |
search |
Full-text search across Drive |
share |
Share a file or folder |
shortcut |
Manage shortcuts to Drive files and folders |
sync |
Reconcile local files with Drive |
tree |
Print a read-only folder tree |
unshare |
Remove a permission from a file |
upload |
Upload a file |
url |
Print web URLs for files |
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.
- today First seen · 62 lines · 10 tokens per session scan A 8323c8945da0
gog-drive is a skill published in the GitHub repository openclaw/gogcli (8,363 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 595 once invoked, about $0.0001 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
cnki-export
Export paper from CNKI and push to Zotero, or save as RIS file. Use when user wants to save a paper to Zotero or export citation data.
ieee-download
Downloads PDF from IEEE Xplore articles. Requires institutional or subscriber access. Use when the user wants to download a paper PDF by article number.
ieee-export
Exports citations from IEEE Xplore in RIS, BibTeX, or plain text format. Supports pushing to Zotero. Use when the user wants to export or save citation data for papers.
cnki-download
Download a paper PDF/CAJ from CNKI. Requires user to be logged in. Use when user wants to download a specific paper.
maket-review
Review and fix Maket documents — audit HTML quality, charte compliance, image paths, layout issues, and automatically apply corrections with makethtml patch. Use this skill when the user says "review", "check", "fix", "audit", "correct", "improve" a document, or when they report visual problems like broken images…
maket
Orientation skill for Maket visual document work. Use when the user asks Claude to design, edit, review, or learn Maket; call maketlearn first for live product guidance, then operate through MCP tools.