ConnectOnion is an open-source, template-first toolkit for building, debugging, deploying, and operating AI agents. Developers use its command-line tools and Python runtime to create agents, add tools, connect services, deploy them, and make them callable by other agents, while the catalogue entries are related agents, 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 skills add openonion/connectonion --skill co-googlegit clone --depth 1 https://github.com/openonion/connectonionWrote 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/openonion/connectonion/co-google)<a href="https://agentmods.dev/skills/openonion/connectonion/co-google"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-google/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/openonion/connectonion/co-google"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-google.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00909 |
| Opus 5.5 | $0.00010 | $0.00364 |
| Sonnet 5.5 | $0.00005 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
co-google 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 1mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Environment selection in the 1.8.4 implementation
Global keys.env is the default for every setting and account. To use a project
file, put --env-file before the command: co --env-file /absolute/path/.env gmail inbox. Auth and refresh use that selected file. No project env loads implicitly;
process overrides remain explicit and provider fields are kept as whole records.
co env (same selector) shows which file is in use and what it holds — run it
first when a command says "not connected in ". See
docs/cli/environment.md for migration and error recovery.
Google tools
| Task | Command family |
|---|---|
| Mail and drafts | co gmail --help (see co-mail-and-drive skill) |
| Files and exports | co gdrive --help (see co-mail-and-drive skill) |
| Events and Meet links | co gcalendar --help |
| Channels and videos | co youtube --help |
Connect with co auth google. Default requests Gmail send/read/modify, Calendar,
Drive and YouTube management, plus email/profile identity. It does not grant every
Google API. Google shows the actual consent screen; declined capabilities are not
invented. Tokens and actual scopes are saved on this computer, not in a remote
credential table. Restricted example: co auth google --scopes youtube.readonly.
Calendar
co gcalendar list prints event IDs, not reusable row numbers.
co gcalendar today
co gcalendar read EVENT_ID
co gcalendar meetings --days 7
co gcalendar free 2026-09-07 --minutes 30
co gcalendar create "Review" "2026-09-07T10:00:00+10:00" "2026-09-07T11:00:00+10:00"
co gcalendar meet "Review" "2026-09-07T10:00:00Z" "2026-09-07T11:00:00Z" --attendees [email protected]
co gcalendar update EVENT_ID --title "New title"
co gcalendar delete EVENT_ID
Mutations above preview locally. Review the exact arguments, then add --yes
only with user approval. Primary calendar only. Naive timestamps mean UTC;
free slots use 09:00–17:00 UTC and do not check attendees' calendars. Empty update
fields do not clear existing fields. A transport failure may have completed a write:
inspect the listing before retrying.
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.
- 1mo ago Changed · +2 lines fdb3fe6597ee
- 1mo ago Changed · +9 lines 00b7a2f02225
- 1mo ago Changed · +2 lines d3704736c47c
- 1mo ago First seen · 69 lines · 25 tokens per session scan A 5e83e78cee4b
co-google is a skill published in the GitHub repository openonion/connectonion (1,501 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 909 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 2026-09-06.
Other skills, from other repositories
agent-initialization
Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt, before tool calls, or after a task). For an Agent with an in-app workbench, pair with penguin-plugin; for a standalone…
computer-history
Answer questions about what the user recently did on their computer — who contacted them, what they were working on, where they left off — by reading the local Computer History summaries and raw event streams.
computer-use
Choose Memmy browser, desktop Computer Use, or a structured connector for a live task on macOS or Windows 11; keep Computer History retrieval separate from UI actions.
cron
Schedule reminders and recurring tasks.
AgentMail
Give the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. [email protected]).
Apple Notes
Open Notes.app and create or update iCloud notes on macOS using memo when possible and AppleScript when direct app automation is more reliable.