← Back to Skills Marketplace
🔌

AgentMail

by OOMOL · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
51
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install oo-agent-mail
Description
AgentMail (agentmail.to). Use this skill for ANY AgentMail request — reading, creating, and updating data. Whenever a task involves AgentMail, use this skill...
README (SKILL.md)

AgentMail

Operate AgentMail through your OOMOL-connected account. This skill calls the agent_mail connector with the oo CLI; OOMOL injects credentials server-side, so you never handle raw tokens.

Category: Communication, Productivity. Exposes 5 action(s).

Running an action

Assume the user has already installed the oo CLI, signed in, and connected AgentMail. Do not run oo auth login or open the connection URL proactively — just run the action. Fall back to First-time setup only when a command actually fails with an auth or connection error.

1. Inspect the contract to get the authoritative input/output schema before building a payload:

oo connector schema "agent_mail" --action "\x3Caction_name>"

2. Run the action with a JSON payload that matches the input schema:

oo connector run "agent_mail" --action "\x3Caction_name>" --data '\x3Cjson>' --json
  • --data takes a JSON object string or @path/to/file.json; omit it to send {}.
  • The response is { "data": ..., "meta": { "executionId": "..." } }; the execution id lives under meta.executionId.

Each action below links to a reference file with its purpose and exact commands. Read the linked file, then fetch the live schema with oo connector schema before constructing --data.

Available actions

  • create_inbox — Create a new AgentMail inbox.
  • get_message — Get a single message from a specific AgentMail inbox.
  • list_inboxes — List inboxes available to the current AgentMail API key.
  • list_messages — List messages from a specific AgentMail inbox.
  • send_message — Send a message from a specific AgentMail inbox.

Safety

  • Read actions (get / list / search) are safe to run directly.
  • Create, update, send, or post actions change AgentMail state — confirm the exact payload and effect with the user before running.
  • Delete or remove actions are destructive — always confirm the target and get explicit approval first.

First-time setup

These are one-time steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.

  • oo: command not found — install the oo CLI (other platforms: \x3Chttps://cli.oomol.com/install-guide.md>):

    curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
    
    irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell
    
  • Not signed in / authentication error — sign in to your OOMOL account once:

    oo auth login
    
  • scope_missing / credential_expired / app_not_ready / app_not_found — AgentMail is not connected, or the connection expired or lacks a scope. Connect once (auth type: API key) at:

    https://console.oomol.com/app-connections?provider=agent_mail
    
  • HTTP 402 / OOMOL_INSUFFICIENT_CREDIT — billing stop. Recharge at https://console.oomol.com/billing/token-recharge before retrying.

Resources

Usage Guidance
This can be treated as benign based on the available clean telemetry, but install only if the skill listing and files match the expected publisher and purpose because the underlying artifact was not available here for independent content review.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
The supplied SkillSpector result is clean and no concrete artifact-backed behavior was provided that would show purpose-mismatched capability.
Instruction Scope
No prompt-injection indicators or unsafe instruction-scope findings were supplied, and no conflicting runtime instructions were available to review.
Install Mechanism
No install metadata or package contents for the target skill version were accessible, so no install-time behavior could be independently validated.
Credentials
The available telemetry shows no malicious, suspicious, or detected engine results and no non-VT malicious signal.
Persistence & Privilege
No evidence was supplied or found showing persistence, privilege escalation, credential access, or background execution.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install oo-agent-mail
  3. After installation, invoke the skill by name or use /oo-agent-mail
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Adds AgentMail support through the OOMOL `agent_mail` connector and `oo` CLI. - Enables inbox management with actions to create inboxes and list available inboxes. - Supports message workflows for listing messages, fetching a single message, and sending mail from an inbox. - Uses live connector schemas before execution so payloads stay aligned with upstream AgentMail contracts. - Keeps credentials server-side through OOMOL and flags state-changing actions for confirmation. Source: `oomol-lab/skills@c600cfc`
Metadata
Slug oo-agent-mail
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is AgentMail?

AgentMail (agentmail.to). Use this skill for ANY AgentMail request — reading, creating, and updating data. Whenever a task involves AgentMail, use this skill... It is an AI Agent Skill for Claude Code / OpenClaw, with 51 downloads so far.

How do I install AgentMail?

Run "/install oo-agent-mail" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is AgentMail free?

Yes, AgentMail is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does AgentMail support?

AgentMail is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created AgentMail?

It is built and maintained by OOMOL (@oomol); the current version is v1.0.0.

💬 Comments