Build Your Own OpenClaw is a step-by-step tutorial and runnable codebase for creating an AI agent, progressing from a chat loop to tools, skills, memory, web access, event-driven operation, channels, scheduling, and multiple agents. It is intended for people learning how agent systems are built, and the catalogue entries correspond to skills used in the example project.
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.
npx skills add czl9707/build-your-own-openclaw --skill cron-opsgit clone --depth 1 https://github.com/czl9707/build-your-own-openclawWrote 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.
[](https://agentmods.dev/skills/czl9707/build-your-own-openclaw/cron-ops)<a href="https://agentmods.dev/skills/czl9707/build-your-own-openclaw/cron-ops"><img src="https://agentmods.dev/badge/skills/czl9707/build-your-own-openclaw/cron-ops/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/czl9707/build-your-own-openclaw/cron-ops"><img src="https://agentmods.dev/badge/skills/czl9707/build-your-own-openclaw/cron-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00013 | $0.00619 |
| Opus 5.5 | $0.00005 | $0.00248 |
| Sonnet 5.5 | $0.00003 | $0.00124 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade C, and why
cron-ops scanned grade C with 1 finding 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf {{crons_path}}/<cron-name> How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help users manage scheduled cron jobs in pickle-bot.
What is a Cron?
A cron is a scheduled task that runs at specified intervals. Crons are stored as CRON.md files at {{crons_path}}/<name>/CRON.md.
Schedule Syntax
Standard cron format: minute hour day month weekday
Examples:
0 9 * * *- Every day at 9:00 AM*/30 * * * *- Every 30 minutes0 0 * * 0- Every Sunday at midnight
One-Off Jobs
Set one_off: true for jobs that should run only once. After execution, the cron is automatically deleted.
Use this for:
- Reminders at a specific future time
- Scheduled one-time tasks
- Delayed notifications
Operations
Create
- Ask what task should run and when
- Determine the schedule
- Ask which agent should run the task
- Ask for a brief description of what the cron does
- If the task should run only once (e.g., "remind me tomorrow"), set
one_off: true - Create the directory and CRON.md file
List
Use bash to list directories:
ls {{crons_path}}
Delete
- List available crons
- Confirm which one to delete
- Use
bashto remove:
rm -rf {{crons_path}}/<cron-name>
Cron Prompt Guidelines
Cron jobs run in the background with no direct output to the user. The agent executing the cron has no conversation context.
When the user asks to be notified (e.g., "tell me", "let me know", "remind me"):
- Include
post_messageinstruction in the prompt
When the user doesn't ask for notification:
- No
post_messageneeded (e.g., background cleanup, data processing)
Cron Template
---
name: Cron Name
description: Brief description of what this cron does
agent: pickle
schedule: "0 9 * * *"
one_off: false # Set to true for one-time jobs (optional, defaults to false)
---
Task description for the agent to execute.
With notification:
---
name: Daily Summary
description: Sends a daily summary of activity
agent: pickle
schedule: "0 9 * * *"
---
Check my inbox and use post_message to send me a summary.
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.
- 2mo ago First seen · 105 lines · 13 tokens per session scan C 3a6fb42de349
cron-ops is a skill published in the GitHub repository czl9707/build-your-own-openclaw (1,912 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 619 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
apple-reminders
Apple Reminders via remindctl: add, list, complete.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
box
Box manages cloud files, sharing, search, and metadata.
obsidian
Read, search, create, and edit notes in the Obsidian vault.
channels-setup
Use when a developer wants to build their first CopilotKit Channels agent and get it answering in Slack or Microsoft Teams: "set up a channel", "connect my agent to Slack", "get my agent into Teams", or starting from nothing and wanting a working channel end to end. Covers the whole path: inspecting or scaffolding the…
mantis-configure
Configures and validates Mantis pipeline environments, sandbox mechanisms, and AI models. Use to set up workflow.json, auto-detect host capabilities, switch between sandboxes (static-only, gvisor, microsandbox, gce), select AI models, and run fast 1-2s preflight tests. Don't use for scanning source code or running…