scheduler

scheduler is a skill for Claude Code from jshchnz/claude-code-scheduler. It costs 219 tokens per session (1,405 once invoked), scanned A, original, MIT.

A scheduling assistant for setting Claude Code tasks to run once or repeat at specified times. It understands plain requests such as “every weekday at 9am” and can use your operating system’s scheduler.

In plain words
What is it for?
Use it to schedule reviews, tests, reminders, audits, and tasks that make changes in an isolated Git worktree, which is a separate working copy of the code.
Why use it?
It turns time-based requests into scheduled jobs, so routine work can happen without manual starts.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Part of the scheduler plugin — 1 skill, 7 commands shipped together

Good fit Use it to schedule reviews, tests, reminders, audits, and tasks that make changes in an isolated Git worktree, which is a separate working copy of the code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jshchnz/claude-code-scheduler/scheduler
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 jshchnz/claude-code-scheduler --skill scheduler
Clone the repo
git clone --depth 1 https://github.com/jshchnz/claude-code-scheduler

Made for: Claude Code.

Or install scheduler, the plugin that ships this one along with the rest of its 1 skill, 7 commands.

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.

agentmods badge for scheduler

README.md
[![agentmods](https://agentmods.dev/badge/skills/jshchnz/claude-code-scheduler/scheduler.svg)](https://agentmods.dev/skills/jshchnz/claude-code-scheduler/scheduler)
Your own site
<a href="https://agentmods.dev/skills/jshchnz/claude-code-scheduler/scheduler"><img src="https://agentmods.dev/badge/skills/jshchnz/claude-code-scheduler/scheduler.svg" alt="Measured on agentmods" height="20"></a>
Per session 219 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,405 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. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk pass 15 Feb 2026
How audits are shown
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 5.1 $0.00219 $0.01405
Opus 5 $0.00110 $0.00702
Sonnet 5 $0.00044 $0.00281
Haiku 4.5 $0.00022 $0.00140

Measured 6d ago against content hash c5940b79686b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

scheduler 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/parse-cron.py, scripts/setup-crontab.sh, scripts/setup-launchd.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/scheduler/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scheduling Assistant

You help users set up and manage scheduled Claude Code tasks. You can:

  • Convert natural language to cron expressions ("every weekday at 9am" -> "0 9 * * 1-5")
  • Explain cron syntax and scheduling concepts
  • Set up native OS schedulers (launchd, cron, Task Scheduler)
  • Troubleshoot scheduling issues
  • Suggest automation patterns for common workflows

Quick Start

To create a scheduled task:

/scheduler:schedule-add

To view all scheduled tasks:

/scheduler:schedule-list

One-Time vs Recurring Tasks

The scheduler supports both one-time and recurring tasks:

One-Time Tasks

For tasks that run once at a specific time:

  • "run at 3pm today"
  • "tomorrow at noon"
  • "next Tuesday at 2pm"

One-time tasks automatically clean up after execution.

Recurring Tasks

For tasks that repeat on a schedule:

  • "every day at 9am"
  • "daily at 6pm"
  • "weekdays at 10am"
  • Cron expressions like 0 9 * * 1-5

Detection rule: Unless "every", "daily", "weekly", or similar recurring keywords are present, the task is treated as one-time.

Git Worktree Mode (Isolated Branches)

For tasks that make changes, worktree mode runs them in isolation:

You: Every night at 2am, refactor deprecated API calls and push for review

Claude: Should this run in an isolated git worktree?
        → Yes, create branch and push changes
        → No, run in main working directory

You: Yes

Claude: ✓ Task created with worktree isolation
        Branch prefix: claude-task/
        Remote: origin

How it works:

  1. Task triggers → creates fresh worktree with new branch
  2. Claude runs in the worktree (isolated from main)
  3. Changes are committed and pushed to remote
  4. Worktree is cleaned up after successful push
  5. You review the PR at your convenience

Configuration options:

Option Default Description
worktree.enabled false Enable worktree isolation
worktree.branchPrefix "claude-task/" Branch name prefix
worktree.remoteName "origin" Remote to push to

Read the full file on GitHub · 168 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 168 lines · 219 tokens per session scan A c5940b79686b

Subscribe to this mod's changes

scheduler is a skill published in the GitHub repository jshchnz/claude-code-scheduler (510 stars, last pushed 7mo ago), licensed MIT. It adds 219 tokens to every session and 1,405 once invoked, about $0.0011 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.