create-system-routine

create-system-routine is a skill for Claude Code, Codex from lvndry/jazz. It costs 34 tokens per session (2,801 once invoked), scanned B, original, MIT.

A tool for scheduling scripts and commands at the operating-system level. It uses cron on Linux and launchd on macOS; Windows Task Scheduler must be configured manually.

In plain words
What is it for?
Use it to schedule shell scripts, programs, or specific commands on a recurring time-based schedule.
Why use it?
It lets routine computer tasks run automatically without someone starting them in a terminal. It also accounts for the security risks of unattended commands and stored secrets.

Skill for Claude CodeCodex

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/lvndry/jazz/create-system-routine
Any agent
npx skills add lvndry/jazz --skill create-system-routine
Clone the repo
git clone --depth 1 https://github.com/lvndry/jazz

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,801 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.02801
Opus 5 $0.00017 $0.01401
Sonnet 5 $0.00007 $0.00560
Haiku 4.5 $0.00003 $0.00280

Measured 3d ago against content hash 91f66fb854d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

create-system-routine scanned grade B 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Never inline secrets (API keys, tokens, passwords) in the cron line or plist. Load them from a file with restricted permissions (e.g. `chmod 600`) inside the wrapped script, or from the environment.
skills/create-system-routine/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create System Routine

When to use this skill

Use this skill when the user wants to create or manage time-based routines (scheduled tasks) at the OS level (e.g., running a shell script, a binary, or a specific command).

  • Linux → use cron (crontab -e, system/user crontabs)
  • macOS → use launchd (LaunchAgents / LaunchDaemons with plist files)
  • Windows → this skill should not create routines; instead, explain that Windows Task Scheduler must be configured manually.

Security

A scheduled routine runs unattended, in the invoking user's context, with no terminal and no chance to answer a prompt.

  • Never inline secrets (API keys, tokens, passwords) in the cron line or plist. Load them from a file with restricted permissions (e.g. chmod 600) inside the wrapped script, or from the environment.
  • Prefer wrapping the real work in a script and calling that script. This keeps PATH, environment, and error handling in one auditable place.
  • The routines this skill creates are user-level and run with the user's privileges. Do not schedule commands that escalate privileges or mutate system state without explicit confirmation.
  • Always explain what will change and keep a backup (e.g. crontab -l > /tmp/crontab.bak) before any destructive edit.

Workflow

  1. Detect the operating system

    Use standard OS detection via shell commands:

    uname_s=$(uname -s 2>/dev/null || echo unknown)
    case "$uname_s" in
      Linux)   os=linux ;;
      Darwin)  os=macos ;;
      MINGW*|MSYS*|CYGWIN*|Windows_NT) os=windows ;;
      *)       os=unknown ;;
    esac
    
    • If os=linux → follow the Linux / cron workflow.
    • If os=macos → follow the macOS / launchd workflow.
    • If os=windows or os=unknown → explain that this skill does not create routines on this OS and suggest Windows Task Scheduler or another platform-specific mechanism.
  2. Gather routine parameters from the user (questionnaire if needed)

    Do not create the cron entry or plist until you have enough information. If the user's request is vague (e.g. "schedule something", "run a script daily") or missing any of the items below, guide them through a short questionnaire instead of guessing.

Read the full file on GitHub · 267 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.

  1. 3d ago First seen · 267 lines · 34 tokens per session scan B 91f66fb854d9

Subscribe to this mod's changes

create-system-routine is a skill published in the GitHub repository lvndry/jazz (50 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 2,801 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

channel_message

Use this skill to proactively send a one-way message to a user/session/channel, usually only when the user explicitly asks to send to a channel/session or when proactive notification is needed. First query sessions with qwenpaw chats list, then push with qwenpaw channels send.

agentscope-ai/QwenPaw · 58 tokens

discord

Use when you need to control Discord from Otto via the discord tool: send messages, react, post or upload stickers, upload emojis, run polls, manage threads/pins/search, create/edit/delete channels and categories, fetch permissions or member/role/channel info, set bot presence/activity, or handle moderation actions in…

elizaOS/eliza · 70 tokens

tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate…

elizaOS/eliza · 87 tokens

obsidian-vault

Organize Obsidian vaults with MOCs, wikilinks, frontmatter/properties, dashboards, orphan-note checks, and cleanup workflows. Use ONLY when the user explicitly refers to Obsidian — by naming "Obsidian", an Obsidian "vault", or an Obsidian-specific feature such as wikilinks ("[[ ]]"), the Dataview or Bases plugins, or…

wonderwhy-er/DesktopCommanderMCP · 171 tokens

local-tools

Access local system resources including Calendar on macOS and Windows. Use this skill when you need to manage user's schedule directly on their device.

netease-youdao/LobsterAI · 30 tokens

imap-smtp-email

Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.

netease-youdao/LobsterAI · 82 tokens