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 agentmods add skills/daxaur/openpaw/c-schedulenpx skills add daxaur/openpaw --skill c-schedulegit clone --depth 1 https://github.com/daxaur/openpawWrote 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/daxaur/openpaw/c-schedule)<a href="https://agentmods.dev/skills/daxaur/openpaw/c-schedule"><img src="https://agentmods.dev/badge/skills/daxaur/openpaw/c-schedule.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.00843 |
| Opus 5 | $0.00015 | $0.00421 |
| Sonnet 5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
c-schedule 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Scheduling
Automate recurring tasks with Claude. Jobs run on a schedule via launchd (macOS) or cron (Linux), with built-in cost caps to prevent runaway spending.
Managing Schedules
# Add a scheduled job (inline)
openpaw schedule add "weekdays 8am" --run "check email and summarize the important ones"
openpaw schedule add "daily 9pm" --run "review today's GitHub notifications"
openpaw schedule add "every 30 minutes" --run "check if any urgent emails arrived" --model haiku
# Interactive mode (prompts for all options)
openpaw schedule add
# List all jobs
openpaw schedule list
# Remove a job
openpaw schedule remove <id>
# Manually trigger a job
openpaw schedule run <id>
# Enable/disable without removing
openpaw schedule enable <id>
openpaw schedule disable <id>
# View cost usage
openpaw schedule costs
# Set daily cost cap
openpaw schedule set-cap 10.00
Schedule Syntax
Human-readable formats:
weekdays 8amorweekdays 08:00daily 9pmordaily 21:00weekends 10amevery 30 minutesevery 2 hoursmonday 9am,friday 5pm, etc.- Raw cron:
0 8 * * 1-5
Cost Control
- Daily cap: $5/day by default — jobs are skipped if the cap would be exceeded
- Per-run budget: Each job has its own budget cap (default $1.00)
- Cost tracking: All costs logged to
~/.config/openpaw/schedule-costs.json - 30-day history: Old entries auto-pruned
- View anytime:
openpaw schedule costs
Delivery Methods
- telegram — results sent directly to your Telegram (requires Telegram bridge setup)
- file — saved to
~/.config/openpaw/schedule-results/(always saved as backup) - notify — macOS notification via terminal-notifier
How It Works
- Jobs are stored in
~/.config/openpaw/schedules.json - Each job registers as a system scheduler:
- macOS: launchd plist in
~/Library/LaunchAgents/ - Linux: crontab entry
- macOS: launchd plist in
- When triggered,
openpaw schedule run <id>is called - Claude runs with the job's prompt via the Agent SDK
- Results are delivered to the configured channel
- Cost is recorded
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.
- 6d ago First seen · 99 lines · 31 tokens per session scan A db04d7db0578
c-schedule is a skill published in the GitHub repository daxaur/openpaw (167 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 843 once invoked, about $0.0002 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.
Other skills, from other repositories
cron-scheduler
Schedule and manage automated tasks with cron expressions - create recurring jobs, one-time tasks, natural language scheduling, and cross-platform timer management.
remindme
⏰ simple Telegram reminders for OpenClaw. cron, zero dependencies.
holix-cron
Schedule recurring agent tasks via Holix built-in gateway cron (not crontab or custom scripts).
scheduler
Manage scheduled jobs — create, update, list, run remote agents on cron. Use when setting up recurring tasks, checking job status, or managing automation.
schedule
创建和管理定时任务 - 设置定期自动执行的任务.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.