ariffazil/agentmail
skills/agentmail/SKILL.md
Give Hermes its own email inbox. Send, receive, and manage email autonomously via agent-owned email addresses ([email protected]). Use when you need to send emails, receive replies, manage email threads, sign up for services via email, or communicate with other agents/humans via email.
data-ai
Updated May 1, 2026
$ install --global
skillsauthnpx skillsauth add ariffazil/openclaw-workspace agentmailInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 1, 2026, 4:08 AM48.7s2 files scanned
SKILL.md
- name:
- agentmail
- description:
- Give Hermes its own email inbox. Send, receive, and manage email autonomously via agent-owned email addresses ([email protected]). Use when you need to send emails, receive replies, manage email threads, sign up for services via email, or communicate with other agents/humans via email.
- tags:
- [email, communication, agentmail, mcp]
- version:
- 1.0.0
- author:
- Hermes / arifOS AAA
- license:
- MIT
AgentMail — Agent-Owned Email Inbox
Quick Start
- Create inbox:
create_inbox(username="hermes-agent")→ gets[email protected] - Send:
send_message(inbox_id=..., to=recipient, subject=..., text=...) - Check replies:
list_threads(inbox_id=...)→get_thread(thread_id=...) - Reply:
reply_to_message(message_id=..., text=...)
Available Tools
| Tool | Description |
|------|-------------|
| list_inboxes | List all agent inboxes |
| get_inbox | Get details of a specific inbox |
| create_inbox | Create a new inbox (gets real email address) |
| delete_inbox | Delete an inbox |
| list_threads | List email threads in an inbox |
| get_thread | Get a specific email thread with all messages |
| send_message | Send a new email |
| reply_to_message | Reply to an existing email |
| forward_message | Forward an email |
| update_message | Update message labels/status |
| get_attachment | Download an email attachment |
Configuration
The MCP server is configured in ~/.hermes/config.yaml under mcp.servers.
API key is set via environment variable AGENTMAIL_API_KEY.
Workflows
Send an email
create_inboxif no inbox exists yetsend_message(inbox_id, to=email, subject=subject, text=body)
Check for replies
list_inboxes→ get inbox_idlist_threads(inbox_id=inbox_id)→ list conversation threadsget_thread(thread_id=thread_id)→ read full thread
Reply to an email
get_threadto find the message_idreply_to_message(message_id=msg_id, text=reply_text)
Sign up for a service
create_inbox(username="signup-bot")→ gets inbox address- Use the inbox address to register on the service
list_threadsto check for verification emailget_threadto read the verification code
Constitutional Notes
- F01 AMANAH: No irreversible email deletion without 888_HOLD
- F04 CLARITY: State purpose of email in subject line
- F05 PEACE: No harmful or abusive content
- F12 INJECTION: Sanitize all email inputs (no raw HTML injection)
Limitations
- Free tier: 3 inboxes, 3,000 emails/month
- Free tier sends from @agentmail.to domain only
- Real-time inbound: use
list_threadspolling via cronjob
Verification
Use list_inboxes to confirm the MCP connection is working.
Related Skills
ariffazil/AAA Agentic Governance (AAA-Cockpit, canonical)
development
VerifiedTrustedCommunity
Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.
SKILL.mdUpdated Jun 6, 2026
ariffazil/skill-trigger-linter
development
VerifiedTrustedCommunity
Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.
SKILL.mdUpdated May 27, 2026
ariffazil/skill-creator
development
VerifiedTrustedCommunity
Bootstrap, design, and package new skills. Load when capturing user intent for a new skill or drafting its initial instruction framework.
SKILL.mdUpdated May 27, 2026
ariffazil/Federation Service Health Triage
content-media
VerifiedTrustedCommunity
Diagnose which federation services are up, down, or drifting. Produce a prioritized remediation plan.
SKILL.mdUpdated May 27, 2026