Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add xrgarcia/slashbin-ai-team/plugin install slashbin-harnessWrote 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/xrgarcia/slashbin-ai-team/schedule)<a href="https://agentmods.dev/skills/xrgarcia/slashbin-ai-team/schedule"><img src="https://agentmods.dev/badge/skills/xrgarcia/slashbin-ai-team/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/skills/xrgarcia/slashbin-ai-team/schedule"><img src="https://agentmods.dev/badge/skills/xrgarcia/slashbin-ai-team/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 | $0.00092 | $0.01800 |
| Opus 5.5 | $0.00037 | $0.00720 |
| Sonnet 5.5 | $0.00018 | $0.00360 |
| Haiku 4.5 | $0.00009 | $0.00180 |
Grade A, and why
schedule scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
schedule
Turn "tell me every morning at 7 what my customer reach is" into a job that actually fires.
A scheduled job is a stored prompt. When it fires, this bot runs that prompt unattended and posts the result into a channel. It has the bot's normal tool access, so treat creating one with the same care as running the request yourself.
Commands
All paths come from the environment. Never name a file.
node "$CLAUDE_PLUGIN_ROOT/bin/schedule.mjs" list
node "$CLAUDE_PLUGIN_ROOT/bin/schedule.mjs" add --cron "0 7 * * 1,2,3,4,5" --prompt "..." --by "<who asked>"
node "$CLAUDE_PLUGIN_ROOT/bin/schedule.mjs" wake --in 20m --prompt "..." --note "..." --carry
node "$CLAUDE_PLUGIN_ROOT/bin/schedule.mjs" remove <id>
node "$CLAUDE_PLUGIN_ROOT/bin/schedule.mjs" history [id]
add recurs on a clock. wake happens once, a stated distance from now.
add defaults to the current channel. Pass --channel <id> only if the user
explicitly asks for it to post somewhere else — a job that quietly posts into a
different channel is a surprise nobody wants.
Writing the cron — read this before composing one
The scheduler evaluates * and comma-separated numbers only.
Ranges and steps are not supported. Write 1,2,3,4,5, never 1-5. The
script rejects a range rather than accepting it, because 1-5 would otherwise
parse as 1 and a "weekdays" job would fire on Mondays alone — a wrong schedule
is worse than a rejected one, since nobody notices until it doesn't happen.
Fields are minute hour day month weekday, weekday 0 = Sunday.
| ask | cron |
|---|---|
| every morning at 7 | 0 7 * * * |
| every weekday at 7 | 0 7 * * 1,2,3,4,5 |
| Mondays at 9:30 | 30 9 * * 1 |
| 1st of the month at 8 | 0 8 1 * * |
Times are interpreted in the bot's configured timezone, not the server's.
The prompt matters more than the schedule
The stored prompt runs with no one watching and no conversation around it. Write it to stand alone:
- Bad:
"tell me the reach"— no context, and "me" means nothing at 7am. - Good:
"Post the current customer reach numbers for Acme, with the change since last week. Lead with the number."
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.
- 16d ago Changed d376c8f35d50
- 17d ago Changed f913f472cbcb
- 1mo ago First seen · 155 lines · 92 tokens per session scan A 54801ae613ce
schedule is a skill published in the GitHub repository xrgarcia/slashbin-ai-team (13 stars, last pushed 6d ago), licensed MIT. It adds 92 tokens to every session and 1,800 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 2026-08-30.
Other skills, from other repositories
cron
Schedule reminders and recurring tasks.
tmux
Use when a CLI task needs an interactive terminal or control of a tmux session.
computer-use
Use Avibe's local Computer Use CLI for carefully bounded desktop observation and actions.
usecase-chief-of-staff-briefing
Build a morning/evening executive brief from calendar, inbox, tasks, and optional ops signals.
usecase-inbox-manager
Triage Inbox Agent Today lanes, search mailbox evidence, prepare manual or AI-assisted replies, and suggest cleanup automations with strict confirmation gates.
usecase-newsletter-digest
Summarize newsletter/email feed messages from the last N hours and propose follow-ups.