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 fmind/dot --skill gwsgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/gws)<a href="https://agentmods.dev/skills/fmind/dot/gws"><img src="https://agentmods.dev/badge/skills/fmind/dot/gws/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/fmind/dot/gws"><img src="https://agentmods.dev/badge/skills/fmind/dot/gws.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 | $0.00023 | $0.01013 |
| Opus 5.5 | $0.00009 | $0.00405 |
| Sonnet 5.5 | $0.00005 | $0.00203 |
| Haiku 4.5 | $0.00002 | $0.00101 |
Grade A, and why
gws 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 7d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Workspace CLI
Use gws for Google Workspace automation from the shell: authentication, API discovery, bounded reads, and verified writes across Drive, Docs, Sheets, Gmail, Calendar, and Chat. Prefer the CLI for supported operations; use a connected app when the requested native editing operation needs its document context or capabilities.
Workflow
-
Resolve the profile: check
gws auth statusfor the account and scopes without printing credentials. SetGOOGLE_WORKSPACE_CLI_CONFIG_DIRbefore auth commands to isolate profiles; an existingGOOGLE_WORKSPACE_CLI_TOKENorGOOGLE_WORKSPACE_CLI_CREDENTIALS_FILEcan override stored credentials, so verify the effective identity without echoing those values. -
Inspect the installed command and live schema: use
<command> --helpfor flags andschemafor the API contract. Start without recursive reference expansion; inspect a referenced type separately when needed.gws schema <service.resource.method> gws schema <service.TypeName> -
Start with a bounded read: pass identifiers, filters, and only the needed fields and date range through
--params; use--page-all --page-limit <n>only when every page is needed. It emits NDJSON with one object per page, not one JSON array; keepnextPageToken(and DriveincompleteSearch) infields, because reaching--page-limitwith a remaining token means the result is incomplete.gws drive files list --params '{"pageSize":10,"q":"trashed = false","fields":"nextPageToken,incompleteSearch,files(id,name,mimeType)"}' --format json -
Choose the content path: read service recipes for metadata versus bodies, Docs tabs, Sheets ranges, Gmail MIME/replies, Calendar times, Slides and Drive exports. Prefer a
+helperlisted bygws <service> --helpwhen its documented semantics match the request. -
Prepare writes exactly: resolve the service, stable identifiers or ranges, content, recipients, and sharing effects first. Follow file-based requests to serialize multiline content, separate
--paramsfrom--json, and inspect a--dry-run. It validates request construction, not permissions or server acceptance. For Chat, follow formatting and threads before composing text. -
Write with authority: reuse authority already supplied by the user for the intended create or edit; ask only for missing consequential scope. Sending mail or Chat, destructive changes, and permission changes require explicit authority. Prepare the concrete request before asking for missing approval.
-
Apply the smallest call: no broad search followed by an unreviewed batch mutation; keep retries idempotent with stable request identifiers or a read-before-write guard where the API supports them.
-
Verify by reading back: fetch the changed resource and compare the requested fields; for messages and events, separate accepted API state from recipient-visible delivery.
What ships with it
7 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.
- 7d ago Changed dd3dce9453f9
- 12d ago Changed 5bbf03f868cf
- 14d ago Changed 288673afb4c5
- 15d ago Changed · -2 lines d54142e2c4cf
- 17d ago Changed 2831d3074d07
- 23d ago Changed 44659e1b95c7
- 26d ago Changed dacfe559b471
- 1mo ago Changed · -9 lines · -21 tokens per session b389327804ec
- 1mo ago Changed · +13 lines 970d8d81d3d1
- 1mo ago First seen · 54 lines · 44 tokens per session scan A ab12484f04fd
gws is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,013 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
google-workspace-cli
Use gws across Workspace APIs with schema-first calls, profile isolation, bounded reads, and verified Drive, Docs, Sheets, Gmail, Calendar, or Chat writes.
handover
Write a self-contained follow-up prompt carrying this session's decisions, constraints, and verified findings into a fresh agent session. Use when handing unfinished work to a new context window.
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
telegram
Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…
dotfiles
Chezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec. Do NOT use for installing tools, running doctor, or updating a machine through the dotfiles CLI; use manage-machine.