
Agent Email Cli
- 2.1k installs
- 7 repo stars
- Updated February 28, 2026
- zaddy6/agent-email-skill
agent-email-cli operates the agent-email CLI for disposable inboxes and message polling in agent workflows.
About
The agent-email-cli skill operates the agent-email command for terminal-based email inbox access in LLM and agent automation workflows. Workflow starts by verifying CLI availability with command -v and --help, installing via npm or bun global @zaddy6/agentemail if missing. Create mailboxes with agent-email create, recording email, accountId, and activeEmail from JSON output while never logging passwords or tokens. Read messages with agent-email read, optional --wait and --interval polling, and --full for complete payloads. Show retrieves one message by ID for verification links or codes. Accounts list, use, and remove manage profiles; delete removes processed messages on request. Operational guidance prefers machine-readable JSON summaries with key fields, uses the default alias when unspecified, surfaces JSON error code and hint on failure, retries once on AUTH_REQUIRED, and backs off on RATE_LIMITED 429 responses. A references/commands.md cheat sheet documents JSON field maps.
- Verify CLI, install globally, then create disposable inboxes.
- Never echo or store passwords or tokens from JSON output.
- Poll inboxes with read --wait and --interval for agent workflows.
- show fetches full message bodies for codes and verification links.
- Surface JSON error code and hint; retry once on AUTH_REQUIRED.
Agent Email Cli by the numbers
- 2,066 all-time installs (skills.sh)
- Ranked #581 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: HIGH risk (skills.sh audit)
- Data as of Aug 4, 2026 (Skillselion catalog sync)
agent-email-cli capabilities & compatibility
- Capabilities
- cli install and availability verification · disposable mailbox creation with json field extr · polling read and full message show commands · account profile list, use, and remove management · secret safe output and structured error handling
- Use cases
- orchestration · testing
- Pricing
- Free
What agent-email-cli says it does
Do not record, repeat, or print secret values such as mailbox passwords or tokens.
Prefer JSON-native command output
npx skills add https://github.com/zaddy6/agent-email-skill --skill agent-email-cliAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 2.1k |
|---|---|
| repo stars | ★ 7 |
| Security audit | 2 / 3 scanners passed |
| Last updated | February 28, 2026 |
| Repository | zaddy6/agent-email-skill ↗ |
How does an agent create, poll, and read disposable email inboxes from the terminal?
Operate the agent-email CLI to create disposable inboxes, poll mail, and manage mailbox profiles for agent automation workflows.
Who is it for?
Agent workflows needing verification emails, OTP codes, or inbox polling.
Skip if: Skip for production transactional email or marketing sends; this is disposable inbox tooling.
When should I use this skill?
User needs terminal email inbox access, agent-email commands, or disposable mailbox automation.
What you get
Working mailbox with JSON-safe reads, shows, and profile management without leaking secrets.
- Disposable mailbox address
- Polled message metadata JSON
- Full message content for code extraction
By the numbers
- Documents 4 core commands: create, read, show, and delete
- Supports inbox polling with configurable --wait and --interval flags
- Published as npm package @zaddy6/agentemail for global CLI install
Files
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
1. Verify CLI availability.
command -v agent-email
agent-email --helpIf missing, install:
npm install -g @zaddy6/agentemail
# or
bun install -g @zaddy6/agentemail2. Create a mailbox account.
agent-email createRecord these fields from JSON output:
data.emaildata.accountIddata.activeEmail
Do not record, repeat, or print secret values such as mailbox passwords or tokens.
3. Read latest messages.
agent-email read <email|default>For inbox waiting/polling:
agent-email read <email|default> --wait 30 --interval 2For full message payloads:
agent-email read <email|default> --full4. 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.
5. 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.
6. 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
defaultalias 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
codeandhintfields 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/binor npm global bin path is onPATH.NO_ACTIVE_ACCOUNT: runagent-email createoragent-email use <email>.ACCOUNT_NOT_FOUND: runagent-email accounts listand pick a valid address.EOTPduring 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.
interface:
display_name: "Agent Email CLI"
short_description: "Operate agent-email CLI for mailbox creation and message reads."
default_prompt: "Use this skill to run agent-email commands for creating disposable inboxes, polling for incoming mail, retrieving message details, and managing local account profiles in terminal agent workflows."
Command Reference
Core commands
agent-email create
agent-email read <email|default> [--limit <n>] [--full] [--wait <s>] [--interval <s>]
agent-email show <email|default> <messageId>
agent-email delete <email|default> <messageId>Profile commands
agent-email accounts list
agent-email accounts remove <email|default>
agent-email use <email|default>
agent-email config path
agent-email aboutOutput envelope
All commands return JSON by default:
{
"ok": true,
"command": "create",
"data": {}
}or on failure:
{
"ok": false,
"command": "read",
"error": {
"code": "ACCOUNT_NOT_FOUND",
"message": "...",
"hint": "..."
}
}High-signal fields
create:data.email,data.accountId,data.activeEmailread:data.messages[]withid,from.address,subject,createdAt,seenshow:data.message, optionaldata.source
Do not extract or print secret fields (password, token) in summaries.
Common automation snippets
Read active inbox and extract first message id:
agent-email read default | jq -r '.data.messages[0].id'Fetch full first message:
MSG_ID=$(agent-email read default | jq -r '.data.messages[0].id')
agent-email show default "$MSG_ID"Related skills
How it compares
Use agent-email-cli for quick terminal disposable inboxes; use Resend agent-email-inbox skills when building production inbound-email agents with webhook security controls.
FAQ
What fields should I record after create?
data.email, data.accountId, and data.activeEmail only; never passwords or tokens.
How do I wait for new mail?
Use agent-email read with --wait and --interval, or --full for complete payloads.
What if I get AUTH_REQUIRED?
Rerun once; if it persists, request user intervention to re-establish credentials.
Is Agent Email Cli safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.