octo-scheduler

octo-scheduler is a command for Claude Code from CES-Ltd/Lumi. It costs 13 tokens per session (546 once invoked), scanned A, original, MIT.

A command for controlling a background service that runs scheduled Claude Octopus workflows. It can start, stop, check, or emergency-stop the service.

In plain words
What is it for?
Starting or stopping the scheduler, checking its status, and halting all scheduled activity in an emergency.
Why use it?
It gives developers a single way to control scheduled automation and confirm whether it is running.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Part of the octo plugin — 10 skills, 47 commands shipped together

Good fit Starting or stopping the scheduler, checking its status, and halting all scheduled activity in an emergency.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ces-ltd/lumi/octo-scheduler
View source ↗ CES-Ltd/Lumi
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.

Clone the repo
git clone --depth 1 https://github.com/CES-Ltd/Lumi

Made for: Claude Code.

Or install octo, the plugin that ships this one along with the rest of its 10 skills, 47 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 octo-scheduler

README.md
[![agentmods](https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-scheduler/github.svg)](https://agentmods.dev/commands/ces-ltd/lumi/octo-scheduler)
Your own site
<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-scheduler"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-scheduler/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.

agentmods 80×15 button for octo-scheduler

Your own site · 80×15
<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-scheduler"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-scheduler.svg" alt="Reviewed on agentmods" width="80" 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 546 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00013 $0.00546
Opus 5 $0.00006 $0.00273
Sonnet 5 $0.00003 $0.00109
Haiku 4.5 $0.00001 $0.00055

Measured 11d ago against content hash c0faf8e0bfb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

octo-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 11d 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.

resources/seed/octopus/commands/octo-scheduler.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scheduler

Manage the Claude Octopus scheduled workflow runner daemon.

Usage

${HOME}/.claude-octopus/plugin/scripts/scheduler/octopus-scheduler.sh start
${HOME}/.claude-octopus/plugin/scripts/scheduler/octopus-scheduler.sh stop
${HOME}/.claude-octopus/plugin/scripts/scheduler/octopus-scheduler.sh status
${HOME}/.claude-octopus/plugin/scripts/scheduler/octopus-scheduler.sh emergency-stop

Instructions for Claude

This command supports natural language. The user may invoke it with explicit subcommands OR with conversational requests. You MUST interpret intent and map to the correct action.

Step 1: Parse Intent

Map the user's input to one of these actions:

Intent patterns Action
"start", "run", "launch", "boot up", "turn on" start
"stop", "shut down", "turn off", "kill", "halt" stop
"status", "how is it", "what's running", "check", "is it running", no args status
"emergency", "panic", "abort", "kill everything", "stop all" emergency-stop

If the intent is ambiguous, use AskUserQuestion to clarify.

Step 2: Display Banner

🐙 **CLAUDE OCTOPUS ACTIVATED** - Scheduler Management
⏰ Scheduler: [action description]

Providers:
🔵 Claude - Daemon management

Step 3: Execute and Present

Run the appropriate octopus-scheduler.sh subcommand and present results.

After status, give a human-readable summary:

  • Whether the daemon is running and for how long
  • How many jobs are active
  • Current daily spend
  • If any kill switches are active, explain what they mean and how to clear them

After start, confirm it's running and remind the user to add jobs if none exist.

After emergency-stop, explain what happened and how to recover:

  • "Remove ~/.claude-octopus/scheduler/switches/KILL_ALL to allow restart"

Natural Language Examples

  • "is the scheduler running?" → status
  • "start the scheduler" → start
  • "shut it down" → stop
  • "something's wrong, stop everything" → emergency-stop
  • "what's the scheduler doing?" → status

Read the full file on GitHub · 67 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. 11d ago First seen · 67 lines · 13 tokens per session scan A c0faf8e0bfb8

Subscribe to this mod's changes

octo-scheduler is a command published in the GitHub repository CES-Ltd/Lumi (31 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 546 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 2026-08-30.