/schedule

command: schedule
disable-model-invocation: true
description: "[advanced] Manage scheduled workflow jobs (add via wizard, dashboard, list, remove, enable, disable, logs)"
aliases:
  - jobs
  - cron

Schedule

Manage scheduled workflow jobs for the Claude Octopus scheduler.

Usage

**Preflight — Ensure plugin root is resolvable (run via Bash tool FIRST):**

OCTO_ROOT="${HOME}/.claude-octopus/plugin"
if [[ ! -x "$OCTO_ROOT/scripts/orchestrate.sh" ]]; then
  helper="$OCTO_ROOT/scripts/helpers/ensure-plugin-root.sh"
  if [[ ! -x "$helper" ]]; then
    helper="$(find "${HOME}/.claude/plugins/cache" "${HOME}/Library/Application Support/Claude" "${LOCALAPPDATA:-/dev/null}/Claude" "${XDG_DATA_HOME:-${HOME}/.local/share}/Claude" -maxdepth 8 -path "*/nyldn-plugins/octo/*/scripts/helpers/ensure-plugin-root.sh" -print -quit 2>/dev/null)"
  fi
  [[ -x "$helper" ]] && bash "$helper" >/dev/null 2>&1 || true
fi
test -x "$OCTO_ROOT/scripts/orchestrate.sh" && echo "plugin-root:ok" || echo "plugin-root:missing"

If the output is `plugin-root:missing`, stop and ask the user to run `/octo:setup`.

${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" / `add` with no file** → Guided wizard

MANDATORY COMPLIANCE — DO NOT SKIP

**When the user explicitly invokes `/octo:schedule`, you MUST use the scheduler command paths below.** You are PROHIBITED from inventing job state, editing scheduler files by hand, or bypassing the dashboard/wizard flow.

---

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)

Display banner:

🐙 CLAUDE OCTOPUS ACTIVATED — Job Wizard
⏰ Schedule: Creating a new scheduled job

Providers:
🔵 Claude — Job configuration

**You MUST ask these questions via AskUserQuestion:**

Question 1:
  question: "What should this job do?"
  header: "Task"
  multiSelect: false
  options:
    - label: "Security scan"
      description: "Nightly vulnerability and code quality audit (squeeze workflow)"
    - label: "Research digest"
      description: "Research a topic and summarize findings (probe workflow)"
    - label: "Full review"
      description: "Complete 4-phase Double Diamond analysis (embrace workflow)"
    - label: "Custom task"
      description: "Describe what you want in your own words"

Question 2:
  question: "How often should it run?"
  header: "Schedule"
  multiSelect: false
  options:
    - label: "Every night at 2am"
      description: "cron: 0 2 * * *"
    - label: "Every weekday morning"
      description: "cron: 0 9 * * 1-5"
    - label: "Weekly (Sunday night)"
      description: "cron: 0 22 * * 0"
    - label: "Custom schedule"
      description: "Describe the timing in natural language"

Question 3:
  question: "Which project/directory should it run in?"
  header: "Workspace"
  multiSelect: false
  options:
    - label: "Current directory"
      description: "Use the current working directory"
    - label: "Specify a path"
      description: "I'll enter the full path"

**WAIT for the user's answers before proceeding.**

**After answers, generate the JSON job definition:**

Map user answers: | User says | workflow | cron | |-----------|----------|------| | Security scan | `squeeze` | `0 2 * * *` | | Research digest | `probe` | user's choice | | Full review | `embrace` | user's choice | | Custom | infer from description | parse time expression |

**Cron translation (natural language → cron):** | Phrase | Cron | |--------|------| | every night / nightly | `0 2 * * *` | | every morning / daily | `0 9 * * *` | | weekday mornings | `0 9 * * 1-5` | | weekly / every week | `0 22 * * 0` | | hourly | `@hourly` | | every N minutes | `*/N * * * *` | | every Monday at Xam | `0 X * * 1` |

**Generate job slug:** "Nightly Security Scan" → `nightly-security`

**Show the generated definition for user confirmation:**

{
  "id": "<slug>",
  "name": "<Full Name>",
  "enabled": true,
  "backend": "<detected — see Step 2>",
  "schedule": { "cron": "<expression>" },
  "task": {
    "workflow": "<workflow>",
    "prompt": "<expanded description>"
  },
  "execution": {
    "workspace": "<path>",
    "timeout_seconds": 3600
  },
  "budget": {
    "max_cost_usd_per_run": 5.0,
    "max_cost_usd_per_day": 15.0
  },
  "security": {
    "sandbox": "workspace-write"
  }
}

Ask: "Does this look right? (yes to save / no to adjust)"

---

Step 2: Backend Detection (MANDATORY — run before saving any job)

This step determines which execution backend to use and sets `"backend"` in the job JSON.

**Check 1 — User override wins:**

backend_pref="${OCTOPUS_SCHEDULER_BACKEND:-auto}"

• If `daemon` → set `backend: daemon`, skip