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.
git clone --depth 1 https://github.com/Elnora-AI/elnora-google-workspaceWrote 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/commands/elnora-ai/elnora-google-workspace/gw-setup)<a href="https://agentmods.dev/commands/elnora-ai/elnora-google-workspace/gw-setup"><img src="https://agentmods.dev/badge/commands/elnora-ai/elnora-google-workspace/gw-setup.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00346 |
| Opus 5 | $0.00019 | $0.00173 |
| Sonnet 5 | $0.00008 | $0.00069 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade A, and why
gw-setup 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.
What it actually says
gw-setup
Run the gw-setup skill to bootstrap this plugin end to end. Do everything you can for the user and only stop where a human must click something in Google Cloud.
Load skills/gw-setup/SKILL.md and follow it in order:
- Environment — detect
python3/uv, create the plugin-local.venv, install deps, generate thegwlauncher, and verifygw --version. - Google Cloud OAuth client — the hard part. Offer to drive a browser (via
the Chrome DevTools MCP) through creating a project, enabling the 7 APIs,
configuring the consent screen, and creating a Desktop OAuth client; save
the client JSON to
~/.config/gw/client_secret.json. If the user declines automation, print the exact URLs and click-by-click steps fromgw auth setup. - Authenticate —
gw auth login(localhost callback). - Verify —
gw auth status, then a real read (gw calendar calendarsorgw gmail labels). - Optional — suggest installing
Elnora-AI/knowledge-vaultto enable the CRM / meeting-prep / outreach connector.
Report what succeeded and the one or two manual clicks the user still owes you.
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 First seen · 29 lines · 39 tokens per session scan A 02725aab301e
gw-setup is a command published in the GitHub repository Elnora-AI/elnora-google-workspace (2 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 346 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
google-workspace-setup
One-time setup for the google-workspace-mcp plugin — check prerequisites, create/locate the OAuth client, define accounts, authorize each in the right browser, and wire it into the current project.
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
battle
Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line.
cli-anything-web:list
List all available CLI-Anything-Web CLIs (installed and generated).
zh
A short command that switches Claude Code to Simplified Chinese. It is handled locally by a command hook.
done
Finish a task - document, create PR or merge, close.