Skill

Fail

Audit score 45

agent-email-cli

zaddy6/agent-email-skill

Terminal-based disposable email inbox management for agent workflows and automation.

What is agent-email-cli?

Operate the agent-email CLI to create temporary email accounts, poll for incoming messages, retrieve full message details, and manage multiple mailbox profiles. Use this when your agent needs programmatic email inbox access for verification codes, sign-ups, or automated email-driven workflows.

Create disposable email inboxes on demand
Poll for new messages with configurable wait and interval options
Retrieve full message payloads including body and source for verification links and codes
Manage multiple local mailbox profiles and switch between accounts
Delete processed messages from inboxes
Output results in JSON format for reliable parsing

How to install agent-email-cli

npx skills add https://github.com/zaddy6/agent-email-skill --skill agent-email-cli

Prerequisites

Node.js or Bun runtime
Install via: npm install -g @zaddy6/agentemail or bun install -g @zaddy6/agentemail

Claude Code

Cursor

Windsurf

Cline

How to use agent-email-cli

1.Verify CLI is installed by running: command -v agent-email && agent-email --help
2.Create a new mailbox account: agent-email create (record the email and accountId from JSON output)
3.Read latest messages: agent-email read <email|default> or use --wait 30 --interval 2 to poll
4.Retrieve full message details: agent-email show <email|default> <messageId>
5.List and manage accounts: agent-email accounts list, agent-email use <email>, or agent-email accounts remove <email>
6.Delete processed messages: agent-email delete <email|default> <messageId>

Use cases

Good for

Automating sign-up flows that require email verification
Polling temporary inboxes for OTP codes or confirmation links
Extracting message content for downstream processing in agent workflows
Managing multiple test accounts across different email addresses
Verifying email-based integrations in CI/CD or testing pipelines

Who it's for

AI agents and LLMs automating email-dependent workflows
Developers building email-driven automation scripts
QA engineers testing email verification flows
DevOps engineers setting up automated account provisioning

agent-email-cli FAQ

What should I do if I get a 'command not found' error?

Ensure ~/.bun/bin or your npm global bin path is on your PATH environment variable. Reinstall with npm install -g @zaddy6/agentemail or bun install -g @zaddy6/agentemail.

How do I poll for messages with a timeout?

Use agent-email read <email|default> --wait 30 --interval 2 to wait up to 30 seconds, checking every 2 seconds for new messages.

What if I get NO_ACTIVE_ACCOUNT error?

Run agent-email create to create a new account, or agent-email use <email> to switch to an existing one.

Should I store passwords or tokens from command output?

No. Never echo, store, or log secret values like passwords or tokens. The skill handles credentials securely; only record the email and accountId.

How do I get the full message body including verification links?

Use agent-email show <email|default> <messageId> to retrieve the complete message payload with body and source.

Full instructions (SKILL.md)

Source of truth, from zaddy6/agent-email-skill.

name: agent-email-cli description: Operate the agent-email CLI to create disposable inboxes, poll for new mail, retrieve full message details, and manage local mailbox profiles. Use when the user needs terminal-based email inbox access for LLM or agent automation workflows.

Agent Email CLI

Overview

Use this skill to operate the agent-email command safely and predictably for agent workflows that need inbox access.

Prefer JSON-native command output and return key fields (email, messageId, subject, createdAt, from.address) in your summaries.

Workflow

Verify CLI availability.

command -v agent-email
agent-email --help

If missing, install:

npm install -g @zaddy6/agentemail
# or
bun install -g @zaddy6/agentemail

Create a mailbox account.

agent-email create

Record these fields from JSON output:

data.email
data.accountId
data.activeEmail

Do not record, repeat, or print secret values such as mailbox passwords or tokens.

Read latest messages.

agent-email read <email|default>

For inbox waiting/polling:

agent-email read <email|default> --wait 30 --interval 2

For full message payloads:

agent-email read <email|default> --full

Retrieve one message in detail.

agent-email show <email|default> <messageId>

Use show when you need body/source details for verification links, codes, or full content extraction.

Manage mailbox profiles.

agent-email accounts list
agent-email use <email|default>
agent-email accounts remove <email>

Avoid commands that require entering secrets on the command line in agent logs.

Delete processed/irrelevant message when requested.

agent-email delete <email|default> <messageId>

Operational Guidance

Keep command output machine-readable; avoid forcing human output unless requested.
Prefer default alias when user does not specify an email.
Never echo, store, or summarize secret values (password, token) from command output.
If command fails, surface the JSON error code and hint fields directly.
For auth failures (AUTH_REQUIRED/401), rerun command once and request user intervention if credentials must be re-established.
For rate limits (RATE_LIMITED/429), retry after short delay.

Troubleshooting

command not found: ensure ~/.bun/bin or npm global bin path is on PATH.
NO_ACTIVE_ACCOUNT: run agent-email create or agent-email use <email>.
ACCOUNT_NOT_FOUND: run agent-email accounts list and pick a valid address.
EOTP during npm publish: use npm trusted publishing for CI or publish locally with OTP.

References

For command cheat sheet and JSON field map, read references/commands.md.

Related skills

More from zaddy6/agent-email-skill and the wider catalog.

design-dna

zanwei/design-dna

1.0k installs

godot-development

zate/cc-godot

Expert knowledge of Godot Engine game development including scene creation, node management, GDScript programming, and project structure. Use when working with Godot projects, creating or modifying scenes, adding nodes, writing game scripts, or solving Godot-specific problems.

1.0k installs