Gini Agent is a personal AI-agent runtime that manages conversations, runs, tasks, approvals, memory, skills, jobs, tools, traces, audit events, and runtime health across its clients. It is for an agent that can remember, learn from task outcomes, and operate through desktop or mobile interfaces with user controls. Catalogue add-ons extend the runtime with skills and instructions.
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/open-curiosity/gini-agent/google-workspace-setupnpx skills add Open-Curiosity/gini-agent --skill google-workspace-setupgit clone --depth 1 https://github.com/Open-Curiosity/gini-agentWrote 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/open-curiosity/gini-agent/google-workspace-setup)<a href="https://agentmods.dev/skills/open-curiosity/gini-agent/google-workspace-setup"><img src="https://agentmods.dev/badge/skills/open-curiosity/gini-agent/google-workspace-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 | $0.00023 | $0.06691 |
| Opus 5 | $0.00012 | $0.03345 |
| Sonnet 5 | $0.00005 | $0.01338 |
| Haiku 4.5 | $0.00002 | $0.00669 |
Grade A, and why
google-workspace-setup scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X PATCH -H "Authorization: Bearer $TOKEN" -H "content-type: application/json" \ How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Workspace Setup
One-time onboarding for the Google Workspace skills (google-gmail, google-calendar, google-drive, google-docs, google-sheets, google-meet, google-forms). Installs gws and gcloud, signs the user into their own Google Cloud project, enables the Workspace APIs, captures an OAuth Desktop client through the inline Connect form, and completes gws auth login.
The OAuth client lives in the user's own GCP project. The Client ID and Client Secret are captured through the inline Connect form (request_connector tool) and stored in Gini's encrypted secret store — never write them to chat or logs, and never write client_secret.json to disk.
This skill is idempotent — re-running it re-verifies the install and lets the user widen scopes.
Provisioning vs signing in. The work splits in two: provisioning (install, gcloud auth login, project, APIs, request_connector) runs once, ever; signing in (gws auth login) runs again whenever the user's gws session expires. gcloud is only ever needed for provisioning — never for a re-auth. Step 0 decides which case you're in.
The Flow
This is the exact first-time sequence (Step 0 short-circuits the already-signed-in and stored-client cases before you reach it). Within the first-time flow do not branch into shortcuts, do not pre-ask whether they have an existing OAuth client, do not list completed actions retrospectively. Status messages are action-oriented: what the user must do next.
- The user asks Gini to do a Workspace thing (read mail, check calendar, share a Drive file, etc.).
- Confirm setup with the user.
- Install
gwsandgcloudsilently in the background. - Run
gcloud auth login, which pops up the user's default browser for sign-in. - After they sign in, create the Cloud project and enable the seven Workspace APIs in the background.
- Send a single chat bubble with the last-step instructions (two Cloud Console URLs) and call
request_connector— the inline form renders below the bubble. - After the user pastes the credentials and clicks Save, ask for a tag for this account and call
skill_run google-account-login, which pops up the user's default browser for OAuth consent and registers the tagged account. - After they sign in, the original ask resumes.
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 · 381 lines · 23 tokens per session scan A a7823e0681f3
google-workspace-setup is a skill published in the GitHub repository Open-Curiosity/gini-agent (1,955 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 6,691 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
clinical-reports
Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
gget
Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
hypogenic
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use…