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-mail-and-drivegit 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-mail-and-drive)<a href="https://agentmods.dev/skills/openonion/connectonion/co-mail-and-drive"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-mail-and-drive/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-mail-and-drive"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-mail-and-drive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 73 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00103 | $0.05515 |
| Opus 5 | $0.00051 | $0.02757 |
| Sonnet 5 | $0.00021 | $0.01103 |
| Haiku 4.5 | $0.00010 | $0.00551 |
Grade A, and why
co-mail-and-drive 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 yesterday.
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 — 414 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, what it holds and which
values the shell overrides — run it first when a command says "not connected in
". See docs/cli/environment.md for migration and error recovery.
co gmail / co outlook / co email / co gdrive
The user's own mail and files, from the shell. One authorization, then plain commands.
Read the output, not just the exit code. All four surfaces — co gmail,
co outlook, co email and co gdrive — exit 1 when they fail (#1012 fixed
the co email exception). The output still carries the recovery step; read it.
First: which mailbox does the user mean?
| Command | Whose mailbox | Ask for it when |
|---|---|---|
co gmail |
the user's personal Gmail | "my email", "my inbox", "reply to Bob" |
co outlook |
the user's personal Outlook | same, on the Microsoft account |
co email |
the agent's own address (*@mail.openonion.ai) |
"send from the agent", "what did the agent receive" |
co gdrive |
the user's Google Drive | "my files", "that doc" |
co outlook calendar |
the user's Outlook calendar | "my meetings", "am I free", "book a Teams call" (Google: co gcalendar) |
When both mail accounts are connected and the request is ambiguous, ask which one rather than guessing. Sending from the wrong identity is not undoable.
Read mail
co gmail # bare command = inbox, 10 most recent
co gmail inbox -n 25 -u # last 25, unread only
co gmail read 3 --listing <listing-id> # token from the displayed listing
co gmail search "from:[email protected] is:unread" # -n to widen
co gmail sent -n 20
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.
- yesterday Changed · +53 lines · +11 tokens per session ad1a93034486
- 3d ago Changed · +70 lines a94ca9ab5547
- 5d ago Changed · +79 lines · +2 tokens per session 0c94a8aeea56
- 11d ago First seen · 212 lines · 90 tokens per session scan A 608df4086cfd
co-mail-and-drive is a skill published in the GitHub repository openonion/connectonion (1,480 stars, last pushed yesterday), licensed Apache-2.0. It adds 103 tokens to every session and 5,515 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When GLM needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When GLM needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing…
google-workspace
Operate across Docs, Sheets, Drive, Gmail, and Calendar with a bias toward clean cross-tool handoffs.
pptx
PPT/PPTX dedicated skill - MANDATORY RULE: For ANY PPT-related tasks (uploaded files, editing/creating presentations, etc.), you MUST IMMEDIATELY direct users to use AI PPT mode by clicking the 【AI PPT】 button below the input box. DO NOT handle it yourself. The dedicated mode is faster and smarter than regular chat.