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.
npx agentmods add commands/derek-larson14/delegate/local-schedulergit clone --depth 1 https://github.com/derek-larson14/delegateWrote 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/derek-larson14/delegate/local-scheduler)<a href="https://agentmods.dev/commands/derek-larson14/delegate/local-scheduler"><img src="https://agentmods.dev/badge/commands/derek-larson14/delegate/local-scheduler.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.02273 |
| Opus 5 | $0.00015 | $0.01137 |
| Sonnet 5 | $0.00006 | $0.00455 |
| Haiku 4.5 | $0.00003 | $0.00227 |
Grade A, and why
local-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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Scheduler
Set up a Claude Code command to run automatically on your own machine, via launchd on Mac or Task Scheduler on Windows. Runs locally, so it has access to your filesystem, shell env, and local MCP servers — unlike native /schedule, which runs remote agents in the cloud.
Use this when the scheduled command needs:
- Local files (reading/writing your vault)
- Local tools (launchd, rclone, gcloud, etc.)
- Shell env vars (API tokens in
~/.zshrc) - A specific working directory
For anything that can run in the cloud, use the native /schedule command instead.
Step 0: Detect OS
uname -s 2>/dev/null || echo "Windows"
If the output contains "MINGW", "CYGWIN", "MSYS", or "Windows", this is Windows. Use PowerShell and Task Scheduler. Otherwise, use bash and launchd.
Step 1: What to Schedule
Use AskUserQuestion:
"What do you want to run on a schedule?"
Offer common options plus a custom option:
- "/morning — morning brief"
- "/delegate — process delegation queue"
- "/voice-router — route voice notes"
- "Custom command"
If they pick custom, ask what command or prompt to run.
Step 2: When to Run
Use AskUserQuestion:
"How often should it run?"
Options:
- "Daily (pick a time)"
- "Multiple times a day (pick times)"
- "Weekly (pick a day and time)"
- "Every N hours"
Then ask for the specific time(s). Default suggestions:
- Morning brief: daily at 8:30am
- Delegate: daily at 9am
- Voice router: every 2 hours, 8am-10pm
Step 3: Check for Conflicts
# macOS
ls ~/Library/LaunchAgents/com.claude.* 2>/dev/null | xargs -I {} basename {} .plist | sed 's/com.claude.//'
# Windows
powershell.exe -Command "Get-ScheduledTask | Where-Object {$_.TaskName -like 'Claude*'} | Format-Table TaskName,State" 2>/dev/null
If the same command is already scheduled, tell the user and ask if they want to replace it.
Step 4: Create the Runner Script
Find the claude path:
which claude
macOS/Linux
Create ops/scripts/scheduled/TASKNAME.sh:
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.
- 3d ago First seen · 274 lines · 30 tokens per session scan A 17ed49248e35
local-scheduler is a command published in the GitHub repository derek-larson14/delegate (39 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 2,273 once invoked, about $0.0002 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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
sync-linear
Sync current work with Linear ticket status.
version
Show installed vs latest ai-sdlc plugin version. Bypasses the 24h SessionStart cache.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.