A command-line tool for scheduling one-time or recurring computer jobs using ordinary language or standard cron expressions.

Adding, listing, removing, inspecting, and manually running scheduled commands.

It removes the need to remember cron syntax and shows when scheduled jobs are expected to run.

crony — Skill for Claude Code and Codex by lirrensi

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.

Any agent

npx skills add lirrensi/agent-sommelier --skill crony

Clone the repo

git clone --depth 1 https://github.com/lirrensi/agent-sommelier

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/lirrensi/agent-sommelier/crony/github.svg)](https://agentmods.dev/skills/lirrensi/agent-sommelier/crony)

Your own site

<a href="https://agentmods.dev/skills/lirrensi/agent-sommelier/crony"><img src="https://agentmods.dev/badge/skills/lirrensi/agent-sommelier/crony/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lirrensi/agent-sommelier/crony"><img src="https://agentmods.dev/badge/skills/lirrensi/agent-sommelier/crony.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 945 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00069	$0.00945
Opus 5	$0.00034	$0.00473
Sonnet 5	$0.00014	$0.00189
Haiku 4.5	$0.00007	$0.00094

Measured 9d ago against content hash b31e868788ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

crony 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 9d 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.

skills/crony/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crony Skill

Manage cron jobs with natural language scheduling and inspect computed upcoming run times.

Installation Check

crony --help

If not installed:

uv tool install "git+https://github.com/lirrensi/agent-sommelier"

Usage

Add a Job

crony add <name> <schedule> <command>
crony add <name> "<cron_expr>" <command> --cron

The --cron flag treats the schedule as a raw 5-field cron expression instead of natural language:

crony add myjob "*/5 * * * *" "python script.py" --cron
crony add nightly "0 2 * * *" "backup.sh" --cron

Working directory preservation: When a job is added, crony automatically captures the current working directory. When the OS scheduler runs the job, it cds to that directory first, so relative paths in commands work correctly regardless of where the scheduler executes. You can still manually add cd anyway: cd /path/to && command.py

List Jobs

crony list
crony list --sync
crony list --json

crony list shows a Next Run column for one-off and recurring jobs. crony list --json includes a computed next_run field for each job.

Remove Job

crony rm <name>

Run Job Now

crony run <name>

View Logs

crony logs <name>

Schedule Formats

One-off Jobs

crony add backup "in 5m" "python --version"
crony add report "at 15:30" "python send_report.py"
crony add deploy "on 2026-03-10" "python deploy.py"

Recurring Jobs

crony add ping "every 1h" "python --version"
crony add cleanup "every 24h" "python cleanup.py"
crony add weekly "every monday" "python weekly_report.py"
crony add weekday "every weekday" "python daily_check.py"

# Raw cron expression (bypasses natural language parser)
crony add nightly "0 2 * * *" "backup.sh" --cron
crony add every-5min "*/5 * * * *" "python check.py" --cron

Interval Syntax

in 5m, in 1h, in 2d - Relative one-off
at 15:30, at "2026-03-10 10:00" - Absolute one-off
every 1h, every 30m, every 24h - Interval recurring
every monday, every weekday, every weekend - Day-based recurring

Read the full file on GitHub · 123 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.

9d ago First seen · 123 lines · 69 tokens per session scan A b31e868788ae

Subscribe to this mod's changes

crony is a skill published in the GitHub repository lirrensi/agent-sommelier (5 stars, last pushed 7d ago), licensed MIT. It adds 69 tokens to every session and 945 once invoked, about $0.0003 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 2026-08-31.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

crony