A command-line tool for creating and managing scheduled tasks, known as cron jobs. Tasks can send fixed messages or ask an agent a question at set times.

Use it for reminders, regular status checks, and scheduled agent questions sent to messaging channels such as iMessage or DingTalk.

It removes the need to remember and run recurring tasks manually. You can also pause, resume, inspect, delete, or run a task immediately.

cron — Skill for Claude Code and Codex by citedy: A command-line tool for creating and managing scheduled tasks…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/citedy/adclaw/cron

Any agent

npx skills add citedy/adclaw --skill cron

Clone the repo

git clone --depth 1 https://github.com/citedy/adclaw

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/citedy/adclaw/cron.svg)](https://agentmods.dev/skills/citedy/adclaw/cron)

Your own site

<a href="https://agentmods.dev/skills/citedy/adclaw/cron"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/cron.svg" alt="Measured on agentmods" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 706 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00025	$0.00706
Opus 5	$0.00013	$0.00353
Sonnet 5	$0.00005	$0.00141
Haiku 4.5	$0.00003	$0.00071

Measured 4d ago against content hash ad3bf5d16ea5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cron scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

src/adclaw/agents/skills/cron/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scheduled Task Management

Use the adclaw cron command to manage scheduled tasks.

Common Commands

# List all tasks
adclaw cron list

# View task details
adclaw cron get <job_id>

# View task status
adclaw cron state <job_id>

# Delete a task
adclaw cron delete <job_id>

# Pause / Resume a task
adclaw cron pause <job_id>
adclaw cron resume <job_id>

# Run a task immediately (one-time execution)
adclaw cron run <job_id>

Creating Tasks

Two task types are supported:

text: Send a fixed message to a channel on a schedule
agent: Ask the Agent a question on a schedule and send the reply to a channel

Quick Create

# Send a text message every day at 9:00
adclaw cron create \
  --type text \
  --name "Daily Good Morning" \
  --cron "0 9 * * *" \
  --channel imessage \
  --target-user "CHANGEME" \
  --target-session "CHANGEME" \
  --text "Good morning!"

# Ask the Agent a question every 2 hours
adclaw cron create \
  --type agent \
  --name "Check To-Dos" \
  --cron "0 */2 * * *" \
  --channel dingtalk \
  --target-user "CHANGEME" \
  --target-session "CHANGEME" \
  --text "What are my pending to-do items?"

Required Parameters

Creating a task requires:

--type: Task type (text or agent)
--name: Task name
--cron: Cron expression (e.g., "0 9 * * *" means every day at 9:00)
--channel: Target channel (imessage / discord / dingtalk / qq / console)
--target-user: User identifier
--target-session: Session identifier
--text: Message content (for text type) or question content (for agent type)

Create from JSON (Advanced Configuration)

adclaw cron create -f job_spec.json

Cron Expression Examples

0 9 * * *      # Every day at 9:00
0 */2 * * *    # Every 2 hours
30 8 * * 1-5   # Weekdays at 8:30
0 0 * * 0      # Every Sunday at midnight
*/15 * * * *   # Every 15 minutes

Usage Tips

If required parameters are missing, ask the user to provide them before creating the task
Before pausing, deleting, or resuming a task, use adclaw cron list to find the job_id
When troubleshooting, use adclaw cron state <job_id> to check the task status
Commands shown to the user should be complete and ready to copy-paste

Read the full file on GitHub · 97 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

4d ago First seen · 97 lines · 25 tokens per session scan A ad3bf5d16ea5

Subscribe to this mod's changes

cron is a skill published in the GitHub repository citedy/adclaw (35 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 706 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agent-framework ai ai-agents ai-marketing chatbot content-generation

cron