agentmods.dev

schedule-add

schedule-add is a command for coding agents from jshchnz/claude-code-scheduler. It costs 13 tokens per session (2,625 once invoked), scanned A, original, MIT.

A command for creating a scheduled Claude Code task that runs once or repeatedly at a specified time. It collects the task details, schedule, command, project folder, and whether autonomous actions are allowed.

In plain words
What is it for?
Use it to schedule a Claude Code prompt for a future time, on a recurring timetable, in a chosen project directory, with the required permission mode.
Why use it?
It turns a time-based request into a configured task instead of requiring you to remember and start the command manually. It distinguishes one-time schedules from recurring schedules.

Command

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

not rated 510 7mo ago A scan 13 tokens original MIT
View the source file jshchnz/claude-code-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.

agentmods
npx agentmods add commands/jshchnz/claude-code-scheduler/schedule-add
Clone the repo
git clone --depth 1 https://github.com/jshchnz/claude-code-scheduler

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 schedule-add

README.md
[![agentmods](https://agentmods.dev/badge/commands/jshchnz/claude-code-scheduler/schedule-add.svg)](https://agentmods.dev/commands/jshchnz/claude-code-scheduler/schedule-add)
Your own site
<a href="https://agentmods.dev/commands/jshchnz/claude-code-scheduler/schedule-add"><img src="https://agentmods.dev/badge/commands/jshchnz/claude-code-scheduler/schedule-add.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,625 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00013 $0.02625
Opus 5 $0.00006 $0.01313
Sonnet 5 $0.00003 $0.00525
Haiku 4.5 $0.00001 $0.00263

Measured 5d ago against content hash 8fb2049e936c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

schedule-add 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 5d 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.

commands/schedule-add.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Scheduled Task

Help the user create a new scheduled task with proper configuration.

Process

  1. Gather Task Information

    • Ask for a task name (required)
    • Ask for description (optional)
    • Ask for schedule - accept either:
      • Cron expression (e.g., "0 9 * * 1-5")
      • Natural language (e.g., "every weekday at 9am", "today at 3pm")

  2. Detect Schedule Type: One-Time vs Recurring

    One-time indicators (default to one-time):

    • "today at 3pm"
    • "tomorrow at noon"
    • "next Tuesday at 2pm"
    • "at 5:30 PM" (no recurring keyword)
    • "January 15th at 9am"

    Recurring indicators:

    • "every day at 9am"
    • "daily at 6pm"
    • "weekly on Monday"
    • "weekdays at 10am"
    • "every 30 minutes"
    • Explicit cron expression (e.g., "0 9 * * 1-5")

    Rule: Unless "every", "daily", "weekly", "monthly", or similar recurring keywords are present, assume one-time.

  3. Configure Execution

    • Ask for the Claude command or prompt to execute
    • Confirm working directory (default: current project)
    • Ask if task needs autonomous execution (file edits, git operations, running commands)
      • If yes: set skipPermissions: true and add --dangerously-skip-permissions flag
      • If no (read-only analysis): omit the flag
    • If task needs autonomous execution AND project is a git repo, ask about worktree isolation:
      • If yes: set worktree.enabled: true
      • Configure optional settings:
        • branchPrefix: default "claude-task/"
        • remoteName: default "origin"

  4. Validate and Confirm

    • For recurring: show cron expression and next 3 run times
    • For one-time: show exact date/time
    • Confirm with user before creating

  5. Create Task

    • Generate unique task ID
    • For one-time: prefix ID with once.
    • Register with native scheduler

macOS launchd Implementation

Recurring Task Plist

Filename: com.claude.schedule.<id>.plist

IMPORTANT:

  • Do NOT use <key>WorkingDirectory</key> - it causes permission errors in background processes
  • Do NOT use ~ in paths - launchd doesn't expand tilde. Use $HOME instead
  • Use cd inside the bash command for working directory

Read the full file on GitHub · 286 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. 5d ago First seen · 286 lines · 13 tokens per session scan A 8fb2049e936c

Subscribe to this mod's changes

schedule-add is a command published in the GitHub repository jshchnz/claude-code-scheduler (510 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 2,625 once invoked, about $0.0001 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
Related

Other commands, from other repositories

cancel-ralph

Cancel active Ralph Loop.

anthropics/claude-plugins-official · 4 tokens

obsidian-recap

Summarize a time period from the vault - today, week, or month.

eugeniughelbur/obsidian-second-brain · 16 tokens

setup-pm-skills

Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.

mohitagw15856/pm-claude-skills · 36 tokens

release

Perform a full release: generate release notes, bump version, commit, tag, and push.

elirantutia/vibeyard · 0 tokens

statusbar-style

Switch the status-bar style (classic / capsule / hairline).

leeguooooo/claude-code-usage-bar · 13 tokens

engage.actions

Execute Phase 7 - Actions on Objectives and Goal Achievement.

hypnguyen1209/offensive-claude · 11 tokens