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 jxoesneon/Ciel --skill google-workspace-managementgit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/google-workspace-management)<a href="https://agentmods.dev/skills/jxoesneon/ciel/google-workspace-management"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/google-workspace-management/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/jxoesneon/ciel/google-workspace-management"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/google-workspace-management.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 | $0.00026 | $0.00505 |
| Opus 5 | $0.00013 | $0.00253 |
| Sonnet 5 | $0.00005 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
google-workspace-management 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 6d 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.
What it actually says
CIEL ADAPTATION: Google Workspace Management (The Asset Layer)
This skill formalizes the operation of Google Workspace using the gws CLI and native MCP tools.
Asset Operations (CLI & MCP)
- Gmail: List, Read, and Draft. Mandate dry-run verification before sending any email.
- Drive: Search by ID/Owner. upload/Download binary assets. Verify listing after upload.
- Calendar: Check schedule and create Meet spaces. Sync links to Gmail drafts.
- Sheets/Docs: Use range-aware edits (Sheets) and index-aware surgery (Docs). Prohibit full rewrites.
Workspace Workflow (Multi-Step)
- Collect & Archive: Gmail attachment -> Drive Folder -> Summarize in Doc.
- Meet & Greet: Calendar event -> Generate Meet Link -> Email link to attendees.
- Surgical Sheet Edit: Identify the "Working System" (formulas/ranges) before inserting columns.
Authentication & Setup
- Hard Gate: Guide users through
gws auth setupandgws auth loginif credentials are missing. - Scope: Request only the minimum required scopes (Gmail.readonly, Drive.file, etc.).
Anti-Patterns
- The Blind Send: Sending an automated email without showing the draft to the user first.
- Stale Duplicate: Editing an old file version because of drive search ambiguity.
- PII Leakage: Sharing a Sheet with public permissions that contains un-redacted PII.
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.
- 6d ago First seen · 50 lines · 26 tokens per session scan A 6746c6f3c12e
google-workspace-management is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 26 tokens to every session and 505 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
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.
gog
Work with Google Workspace surfaces such as Gmail, Calendar, Drive, Docs, Sheets, and contacts through configured local tools.
feishu
A tool for reading and writing Feishu, also called Lark, which is a workplace collaboration platform. It works with documents, sheets, databases, files, calendars, tasks, wikis, and messages through Feishu's API.
tencent-docs
An interface for Tencent Docs, an online suite for documents, spreadsheets, presentations, mind maps, flowcharts, tables, and forms.
wecom
A connection to WeCom, a workplace messaging and collaboration service used by Chinese companies. It lets an agent work with contacts, messages, documents, smart sheets, schedules, and meetings through a company app.
google-workspace-ops
Operate across Google Drive, Docs, Sheets, and Slides as one workflow surface for plans, trackers, decks, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without dropping to raw tool calls.