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.
git clone --depth 1 https://github.com/CES-Ltd/LumiWrote 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.
[](https://agentmods.dev/commands/ces-ltd/lumi/octo-schedule)<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-schedule"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-schedule/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.
<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-schedule"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-schedule.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00022 | $0.02444 |
| Opus 5 | $0.00011 | $0.01222 |
| Sonnet 5 | $0.00004 | $0.00489 |
| Haiku 4.5 | $0.00002 | $0.00244 |
Grade A, and why
octo-schedule 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.
This is a copy
89% identical to octo-schedule — 32 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schedule
MANDATORY COMPLIANCE — DO NOT SKIP
When the user invokes /octo:schedule, you MUST use the scheduler CLI below. You are PROHIBITED from:
- Managing cron jobs or schedules manually without the scheduler
- Skipping the scheduler subcommands and just editing files directly
- Substituting
crontab -eor manual file edits for the scheduler interface
The user chose /octo:schedule for the managed scheduler workflow.
Manage scheduled workflow jobs for the Claude Octopus scheduler.
Usage
${HOME}/.claude-octopus/plugin/scripts/scheduler/octopus-scheduler.sh [subcommand]
Instructions for Claude
This command supports natural language and provides two primary experiences:
- No args / "show jobs" / "what's scheduled" → Dashboard table
- "add a job" / "schedule X" /
addwith no file → Guided wizard
Step 0: Parse Intent First
| User says | Action |
|---|---|
| No args, "show jobs", "status", "what's scheduled", "list" | Dashboard (Step 1A) |
| Describes a new job, "add", "create", "schedule a...", any time/frequency reference | Wizard (Step 1B) |
| "remove", "delete" + job name/id | Run remove <id> directly |
| "enable", "turn on" + job reference | Run enable <id> |
| "disable", "pause", "turn off" + job reference | Run disable <id> |
| "logs", "what happened", "last run" | Run logs [id] + summarize |
| Wants to change schedule/budget/prompt on existing job | Modify (Step 1C) |
If intent is ambiguous, show the dashboard first, then ask what they'd like to do.
Step 1A: Dashboard (No-args / List)
Display the banner, then run:
${HOME}/.claude-octopus/plugin/scripts/scheduler/octopus-scheduler.sh dashboard
Present the output as-is. After showing it, offer quick actions:
What would you like to do?
• Add a new job
• Enable/disable a job
• View logs for a job
• Remove a job
Step 1B: Wizard — Guided Job Creation (MANDATORY for new jobs without a file arg)
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.
- 11d ago First seen · 316 lines · 22 tokens per session scan A 72d567d1135f
octo-schedule is a command published in the GitHub repository CES-Ltd/Lumi (31 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 2,444 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to octo-schedule, differing in 32 lines, and is treated as a copy.
Other commands, from other repositories
suggest-automation
A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.
evolve
Cluster related instincts into skills, commands, or agents.
instinct-import
Import instincts from teammates, Skill Creator, or other sources.
instinct-export
Export instincts for sharing with teammates or other projects.
context-stats
Display context window usage and token statistics.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.