Borrowing it
Nothing to install: this file belongs to fo0/clawstash. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fo0/clawstash/main/.claude/skills/scheduler/SKILL.mdgit clone --depth 1 https://github.com/fo0/clawstashWrote 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/fo0/clawstash/scheduler)<a href="https://agentmods.dev/skills/fo0/clawstash/scheduler"><img src="https://agentmods.dev/badge/skills/fo0/clawstash/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.
<a href="https://agentmods.dev/skills/fo0/clawstash/scheduler"><img src="https://agentmods.dev/badge/skills/fo0/clawstash/scheduler.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 | $0.00095 | $0.02014 |
| Opus 5.5 | $0.00038 | $0.00806 |
| Sonnet 5.5 | $0.00019 | $0.00403 |
| Haiku 4.5 | $0.00010 | $0.00201 |
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 1mo 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scheduler — Routines, Loops and Cron Jobs
When to Use
- User says "/scheduler", "schedule this", "run this nightly/weekly", "every morning", "remind me in an hour", "check back later"
- The agent itself needs to come back later: waiting on CI, a long Docker build, a GHCR publish, a PR that is not ready yet
- A run is about to end and this session created triggers, cron jobs or PR subscriptions → the cleanup pass below is mandatory
Sub-commands (bare /scheduler routes by what the request asks for):
| Argument | Does |
|---|---|
list |
Every job visible from this surface — CronList, plus list_triggers where the MCP is present |
new |
Create one, after picking the layer in step 1 |
clean |
Run the cleanup contract now instead of at the end of the run |
Scope Boundaries
Owns: when work runs and on which surface, and the cleanup contract for jobs the agent created for its own bookkeeping.
Does not own: how the work is divided once it runs (orca), what a bare /loop actually does (.claude/loop.md), or the cross-turn stop condition — that is Claude Code's own /goal.
1. Pick the layer by lifetime — this is the whole decision
| Need | Layer | How | Lifetime |
|---|---|---|---|
| Runs without this session, machine off, ≥ 1 h apart | Routine (cloud) | see Surfaces below | Durable, until deleted |
| Poll something while this session stays open | /loop or CronCreate |
/loop 10m <prompt> · /loop <prompt> (agent picks the interval) |
This session; recurring jobs expire after 7 days |
| One-off "come back to this later" inside the session | CronCreate one-shot, or plain natural language ("in 45 minutes, check the tests") |
fires once, deletes itself | This session |
| Needs local files / local tools on a schedule | Desktop scheduled task | user creates it in the Desktop app | Durable, machine must be on |
| React to an event instead of polling | not a scheduler | subscribe_pr_activity for PR events, a GitHub trigger on a routine, Monitor for a stream |
— |
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.
- 1mo ago Changed · -1 lines c66550e5933c
- 1mo ago Changed · +7 lines 14515bf32505
- 2mo ago First seen · 102 lines · 95 tokens per session scan A 3b3ee1209763
scheduler is a skill published in the GitHub repository fo0/clawstash (1 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 2,014 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
local-delegation
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…
manage-lounge-history
Review, correct or delete a signed-in user's logged visits and reviews. Requires OAuth with the write scope.
track-lounge-visits
Log a lounge visit, write or edit a review, and manage a wishlist on behalf of a signed-in user. Requires OAuth with the write scope.
lounge-wishlist-and-passport
Show a signed-in user's profile, lounge passport stats and wishlist, and add or remove wishlist lounges. Requires OAuth.
openclaw-telegram-bot
Telegram bot toolkit MCP server with 5 tools for AI agents. Use when: (1) 'send a message to Telegram' or 'notify me on Telegram', (2) 'send an alert' or 'notify on error', (3) 'get latest Telegram messages' or 'check for commands', (4) 'set bot commands menu', (5) 'send daily report to Telegram'. TelegramBridge…
mcptoon
Compress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window…