Skip to main content

Overview

Cron tools let the agent create and manage scheduled jobs. You can schedule HTTP calls (webhooks), execute any profClaw tool automatically, or run shell commands on a cron expression or interval. All cron tools are in the Full tier - they require capable models to correctly reason about cron expressions and job lifecycles.

Available Tools

Tool: cron_create

Create a new scheduled job. Security level: moderate | Tier: Full
string
required
Human-readable name for the job (max 100 characters).
string
Optional description of what the job does.
string
Cron expression (e.g., "*/5 * * * *" for every 5 minutes). Either cron or interval is required.
number
Interval in milliseconds (minimum 1000ms = 1 second). Alternative to cron.
string
default:"http"
Job type: http, tool, or script.

HTTP Job Parameters

string
Webhook URL to call.
string
default:"GET"
HTTP method: GET, POST, PUT, DELETE.
object
Request headers.
any
Request body (JSON-encoded automatically).

Tool Job Parameters

string
Name of the profClaw tool to execute.
object
Parameters to pass to the tool.

Script Job Parameters

string
Shell command to run.
array
Command arguments array.
string
Working directory for the script.

Limits

number
Stop the job after this many successful runs.
number
Pause the job after this many consecutive failures.

Examples

Common Cron Expressions

Tool: cron_list

List all scheduled jobs with status. Returns job IDs, names, schedules, current status (active/paused/archived), last run time, and next scheduled run.

Tool: cron_trigger

Manually trigger a job outside its schedule.
string
required
Job ID to trigger.

Tool: cron_pause

Pause or resume a job.
string
required
Job ID.
boolean
required
true to pause, false to resume.

Tool: cron_history

View the run history for a job.
string
required
Job ID.
number
default:"20"
Maximum history entries.
Returns: run timestamps, duration, status (success/failure), and any error messages.

profClaw Ops

Schedule recurring ticket creation or status updates.

Web Fetch

HTTP jobs use the same SSRF protections as web_fetch.