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 vanducng/skills --skill goggit clone --depth 1 https://github.com/vanducng/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/vanducng/skills/gog)<a href="https://agentmods.dev/skills/vanducng/skills/gog"><img src="https://agentmods.dev/badge/skills/vanducng/skills/gog/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/vanducng/skills/gog"><img src="https://agentmods.dev/badge/skills/vanducng/skills/gog.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 | $0.00083 | $0.03067 |
| Opus 5.5 | $0.00033 | $0.01227 |
| Sonnet 5.5 | $0.00017 | $0.00613 |
| Haiku 4.5 | $0.00008 | $0.00307 |
Grade A, and why
gog scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gog
Google Workspace through gog. This skill is the local account map and safety
wrapper. Discover flags from the binary (gog schema, gog <svc> --help).
Every invocation:
export GOG_HOME="${GOG_HOME:-$HOME/.config/vd/gog}"
# source "$GOG_HOME/env" if present
Never run a bare gog without GOG_HOME. Tokens then land in ~/.config/gogcli
and this skill cannot see them.
A command handed to the person to run (! gog ..., a pasted snippet) runs in
their shell, which does not have this export. Write the prefix inline:
GOG_HOME=$HOME/.config/vd/gog gog --client <client> auth add ....
Flags (prompt / skill args)
vd:gog --account <name> --user <person|sa> <gmail|drive|calendar|sheets|docs|auth> ...
| Flag | Values | Default |
|---|---|---|
--account |
any name in $HOME/.config/vd/gog-accounts/ |
none; required on writes, ask if missing |
--user |
person (human mailbox, refresh token), sa (service account key) |
person |
Discover the configured accounts, never assume them:
ls "$HOME/.config/vd/gog-accounts/"*.md # <account>.user.md / <account>.sa.md
Resolve to a gog CLI identity: --user person → gog --account <account>,
--user sa → gog --account <account>-sa.
Read $HOME/.config/vd/gog-accounts/<account>.<user|sa>.md before the first call.
If that file is missing, stop and say so. Do not invent an email.
--user person is the Gmail/Calendar/Sheets-as-you path. --user sa is only
for Drive/Sheets already shared with that key. Never send mail as --user sa.
Multi-organization architecture
Keep each organization in an explicit identity boundary:
account registry -> named gog client -> Google Cloud OAuth project
-> client secret in keyring
-> person refresh token -> service APIs
- Use one named
--clientper organization or domain; do not sharedefaultacross organizations. - The OAuth project controls audience and enabled APIs. Audience changes affect every client in that project.
- The registry maps
--accountand--user; the named client owns its credentials and token bucket. - OAuth client JSON is bootstrap material. Keep it mode
0600in a gitignored secret store;auth credentials setstores the secret in the keyring unless--insecureis explicit. - Refresh tokens are client-bound. Changing the OAuth project or client does not migrate them; run
auth add --force-consentagain. --servicesgrants scopes during authorization. A multi-service task is one skill request that sequences separate service commands.
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.
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.
- 2d ago Changed · +19 lines 20b97de9d089
- 12d ago Changed · +2 lines 27ec37d5ef3d
- 20d ago Changed 8d0133528b39
- 1mo ago Changed · +3 lines a29bb17dd3d8
- 1mo ago Changed · -3 lines 44334aedd5db
- 1mo ago Changed · +21 lines a591692d4d34
- 1mo ago Changed · +19 lines · +4 tokens per session af9e36ae8cd2
- 1mo ago First seen · 162 lines · 79 tokens per session scan A 8e88c731a1a7
gog is a skill published in the GitHub repository vanducng/skills (8 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 3,067 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 2026-09-11.
Other skills, from other repositories
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…
new-job
This skill should be used when the user wants to add a new company or job to their Excel tracker (List.xlsx). Triggers on phrases like "add [company] to tracker", "I applied to [company]", "track [company]", "save [company] for later", "add [company] [role]", "new application at [company]".
spreadsheet-model-builder
Structures spreadsheet models a second analyst can audit - separated input/calc/output sheets, one-formula-per-row hygiene, built-in error checks, and a documented cover sheet. Use when someone asks "how should I structure this model", "clean up this spreadsheet before the board sees it", "why does my model break when…
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
data-table-design
Designs presentation tables that read correctly at a glance - numeric alignment, consistent precision, deliberate sort order, unit-labeled headers, and well-placed totals - and delivers a before/after redesign of the reader's table. Use when someone asks "make this table more readable", "how many decimals should I…
recipe-grocery-list
Converts one or more recipes, a weekly meal plan, or even just dish names into a clean, categorized, deduplicated grocery shopping list — with quantities scaled to the number of servings needed. Also exports a formatted Excel (.xlsx) shopping list file. Use this skill whenever the user mentions: "make a grocery list"…