# Remote Triggers

> Cross-session automation using RemoteTrigger API. Create, manage, and run scheduled remote agents that execute on cron schedules and survive session exit. Auto-activates on remote trigger, scheduled agent, cross-session, persistent schedule, automated agent, trigger API.

- **Type:** Skill
- **Install:** `agentstack add skill-pfangueiro-claude-code-agents-remote-triggers`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [pfangueiro](https://agentstack.voostack.com/s/pfangueiro)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [pfangueiro](https://github.com/pfangueiro)
- **Source:** https://github.com/pfangueiro/claude-code-agents/tree/main/.claude/skills/remote-triggers

## Install

```sh
agentstack add skill-pfangueiro-claude-code-agents-remote-triggers
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Remote Triggers

Create and manage remote agent triggers that execute on schedules and survive session exit.

## When to Use

- **Persistent schedules**: Tasks that must run even after the session ends
- **Cross-session automation**: Recurring code reviews, automated deploys, health checks
- **Scheduled agents**: Run specific prompts on cron schedules in the background
- **Team automation**: Set up shared triggers that benefit the whole team

## How It Differs from CronCreate

| Feature | CronCreate | RemoteTrigger |
|---------|-----------|---------------|
| Survives session exit | No (session-scoped) | Yes (persistent) |
| Runs while REPL idle | Yes | Yes (server-side) |
| Max duration | 7 days | Unlimited |
| Setup complexity | Low | Medium |
| Requires auth | No | Yes (OAuth) |

**Rule of thumb**: Use CronCreate for in-session monitoring. Use RemoteTrigger for anything that must persist.

## Tool: RemoteTrigger

**Actions:**

### list
List all configured triggers.
```
RemoteTrigger: { action: "list" }
```

### get
Get details of a specific trigger.
```
RemoteTrigger: { action: "get", trigger_id: "my-trigger" }
```

### create
Create a new trigger with a schedule and prompt.
```
RemoteTrigger: {
  action: "create",
  body: {
    name: "nightly-security-scan",
    cron: "0 2 * * *",
    prompt: "Run /security-scan on the entire codebase and report findings",
    enabled: true
  }
}
```

### update
Update an existing trigger (partial update).
```
RemoteTrigger: {
  action: "update",
  trigger_id: "my-trigger",
  body: { enabled: false }
}
```

### run
Manually trigger an immediate execution.
```
RemoteTrigger: { action: "run", trigger_id: "my-trigger" }
```

## Use Case Patterns

### Nightly Security Scan
```
RemoteTrigger create:
  name: "nightly-security-scan"
  cron: "0 2 * * *"
  prompt: "Run /security-scan and create a GitHub issue if critical vulnerabilities are found"
```

### Pre-Release Quality Gate
```
RemoteTrigger create:
  name: "pre-release-check"
  cron: "0 8 * * 1-5"
  prompt: "Check if there are open PRs targeting the release branch. Run /quality-gate on each."
```

### Dependency Update Monitor
```
RemoteTrigger create:
  name: "dep-monitor"
  cron: "0 9 * * 1"
  prompt: "Check for outdated dependencies and create a summary issue if updates are available"
```

## Best Practices

- Use descriptive trigger names — they appear in `list` output
- Start with `enabled: false` and test with `run` before enabling the schedule
- Avoid scheduling during peak hours — spread triggers across off-peak times
- Use `update` to disable triggers temporarily rather than deleting them
- Monitor trigger execution results — failed triggers may need prompt adjustments

## Related

- `scheduled-tasks` skill — Session-scoped scheduling with CronCreate (lighter weight)
- `/schedule` command — Higher-level wrapper for RemoteTrigger
- `experiment-loop` skill — Metric-driven optimization loops

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [pfangueiro](https://github.com/pfangueiro)
- **Source:** [pfangueiro/claude-code-agents](https://github.com/pfangueiro/claude-code-agents)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-pfangueiro-claude-code-agents-remote-triggers
- Seller: https://agentstack.voostack.com/s/pfangueiro
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.