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 skills add JansenAnalytics/claudex --skill schedulergit clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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/skills/jansenanalytics/claudex/scheduler)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/scheduler"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/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 5.1 | $0.00031 | $0.00839 |
| Opus 5 | $0.00015 | $0.00419 |
| Sonnet 5 | $0.00006 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scheduler Skill
Natural language task scheduling for Kite. Create, list, and cancel scheduled jobs in plain English with a human-readable registry of what's running and why.
Quick Trigger Phrases
| User says | Kite does |
|---|---|
| "Schedule X every Y" | node scheduler.cjs add --name "X" --every "Y" --command "..." --why "..." |
| "Remind me to X at Y" | node scheduler.cjs add --name "X" --at "Y" --command "..." --why "..." |
| "What's scheduled?" / "List scheduled tasks" | node scheduler.cjs list |
| "Cancel the morning brief" / "Remove X" | node scheduler.cjs remove morning-brief |
| "Check scheduler health" / "Any drift?" | node scheduler.cjs status |
| "Sync the scheduler" | node scheduler.cjs sync |
Files
- Registry:
~/.openclaw/schedule.json— human-readable source of truth - CLI:
${SCHEDULER_HOME:-$HOME/projects/scheduler}/scheduler.cjs— manages registry + crontab - Skill copy:
${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/scheduler/scripts/scheduler.cjs
Usage
# Add a recurring task
node ${SCHEDULER_HOME:-$HOME/projects/scheduler}/scheduler.cjs add \
--name "Morning brief" \
--every "9am Monday-Friday" \
--command "/usr/bin/node $HOME/scripts/brief.cjs" \
--why "Daily summary of overnight events"
# Add a one-shot reminder
node ${SCHEDULER_HOME:-$HOME/projects/scheduler}/scheduler.cjs add \
--name "Check deployment" \
--at "2026-02-21 18:00" \
--command "/usr/bin/node $HOME/scripts/check-deploy.cjs" \
--why "Verify prod deploy went smoothly"
# List all tasks
node ${SCHEDULER_HOME:-$HOME/projects/scheduler}/scheduler.cjs list
# See what's in crontab vs registry
node ${SCHEDULER_HOME:-$HOME/projects/scheduler}/scheduler.cjs status
# Remove a task
node ${SCHEDULER_HOME:-$HOME/projects/scheduler}/scheduler.cjs remove morning-brief
# Fix drift (sync registry → crontab)
node ${SCHEDULER_HOME:-$HOME/projects/scheduler}/scheduler.cjs sync
# Show all supported time formats
node ${SCHEDULER_HOME:-$HOME/projects/scheduler}/scheduler.cjs help-times
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 85 lines · 31 tokens per session scan A e0de55fcf919
scheduler is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 839 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 2026-09-03.
Other skills, from other repositories
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
cron-doctor
Diagnose and validate cron expressions before they ship. Catches the five silent death-traps: impossible dates that never fire, OR-semantics that fire too often, midnight spikes, uneven step drift, and leap-year February 29.
kickoff
Session bootstrapper. Reads the consolidated handoff, README, development logs, and active baseline to establish session awareness and recommend next tasks. TRIGGER when: user says "/kickoff", "kickoff", "start session", or "boot session".
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
wp-content-workflows
This skill should be used when the user asks about "workflow automation", "triggers", "scheduled tasks", "WP-Cron", "content publishing triggers", "hook-based actions", "post status transitions", "automated notifications", "workflow triggers", "event-driven actions", "content lifecycle hooks", "multi-channel actions"…