Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/kevin-liu-01/agent-machines/automation-cron)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/automation-cron"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/automation-cron/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/kevin-liu-01/agent-machines/automation-cron"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/automation-cron.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 | $0.00044 | $0.00858 |
| Opus 5 | $0.00022 | $0.00429 |
| Sonnet 5 | $0.00009 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
automation-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 12d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automation via Cron
I can schedule recurring tasks via the cronjob tool. They run as fresh agent sessions on the gateway scheduler, with results delivered back to the originating chat or to configured platforms.
Schedule formats
Hermes accepts both natural language and crontab syntax:
"every 1h"
"every 30m"
"every 2h"
"every 1d at 09:00"
"daily at 04:00"
"every monday at 09:00"
"0 9 * * *" # crontab -- daily at 09:00 UTC
"30 */4 * * *" # crontab -- every 4 hours at :30
Creating a job
Three surfaces, same effect:
# CLI
agent-machines cron create "every 1h" "Summarize new feed items" --skill blogwatcher --name "Hourly feeds"
# In-chat slash command
/cron add "0 9 * * *" "Audit my open PRs and post a summary"
# In a tool call
cronjob(
action="create",
schedule="every 1d at 09:00",
prompt="Summarize my last 24 hours of commits across all projects",
name="Daily commit digest",
skills=["git-workflow"],
)
Skill-backed jobs
A cron job can preload one or more skills before running its prompt. Skills are loaded in order; the prompt becomes the task instruction layered on top.
Use this when the job needs a recurring procedure (e.g. blogwatcher checks feeds, llm-wiki updates a knowledge base).
Workdir scoping
By default cron jobs run detached from any repo. Pass workdir to load AGENTS.md / CLAUDE.md and run terminal/file tools rooted in that directory:
cronjob(
action="create",
schedule="every 1d at 09:00",
workdir="/home/machine/projects/dedalus-monorepo",
prompt="Audit open PRs, summarize CI health, and post to #eng",
)
The path must be absolute and exist; relative paths are rejected.
Operations
cronjob action=list # show all jobs
cronjob action=pause id=... # pause a job
cronjob action=resume id=... # resume a job
cronjob action=run id=... # trigger immediately
cronjob action=remove id=... # delete a job
cronjob action=update id=... # edit schedule, prompt, skills, or workdir
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.
- 12d ago First seen · 100 lines · 44 tokens per session scan A ae02e31405d9
automation-cron is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 858 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
holix-cron
Schedule recurring agent tasks via Holix built-in gateway cron (not crontab or custom scripts).
21-day-self-interview
A 21-night guided self-reflection routine in which an agent asks three questions each night, remembers the answers, and reflects on them at key points.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
remindme
⏰ simple Telegram reminders for OpenClaw. cron, zero dependencies.
email-formatting
Markdown formatting conventions for email summary documents — heading depth, list style, line length, emoji policy, and a mandatory provenance footer. Read this when producing a markdown report that summarizes one or more email messages so the output matches the project's house style.
json-schema-emails
Canonical shape of the .workflow/emails/emails.json file passed between the fetch and summarize states — required fields (sender, recipient, subject, date, body), types, and field semantics. Read this whenever you write or read emails.json so producer and consumer agree on the shape.