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 crystal-autobot/autobot --skill crongit clone --depth 1 https://github.com/crystal-autobot/autobotWrote 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/crystal-autobot/autobot/cron)<a href="https://agentmods.dev/skills/crystal-autobot/autobot/cron"><img src="https://agentmods.dev/badge/skills/crystal-autobot/autobot/cron/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/crystal-autobot/autobot/cron"><img src="https://agentmods.dev/badge/skills/crystal-autobot/autobot/cron.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00010 | $0.00614 |
| Opus 5 | $0.00005 | $0.00307 |
| Sonnet 5 | $0.00002 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
cron 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 10d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cron scheduling rules
Job naming
Always provide a short name for every job (max 30 chars). This label is shown in /cron and list output.
Keep it human-readable — describe what the job does, not how.
Bad: "Use the web_search tool to che" Good: "GitHub stars check"
Message quality
The message field is the prompt for a background agent turn that runs without conversation context.
Write it as a self-contained instruction:
- Include the specific action, tool name, URLs, thresholds, and any values the user mentioned
- 50+ words for complex tasks; short reminders can be brief
- Never use pronouns ("check it", "do the thing") — be explicit
Bad: "Check the repo" Good: "Use the web_search tool to check https://github.com/user/repo for new releases published in the last 24 hours. If there is a new release, summarize the changelog."
Timezone handling
- If the user mentions a timezone or city, convert to UTC and confirm both times
- If unclear, ask which timezone they mean before scheduling
- Always store and display schedules in UTC
- Confirm: "Scheduled for 09:00 UTC (11:00 Berlin time), weekdays"
Update-first rule
Before creating a new job, always list existing jobs first.
If a matching job already exists, update it instead of creating a duplicate.
Never create duplicate jobs for the same purpose.
Schedule types
| Type | Parameter | Use case |
|---|---|---|
| Interval | every_seconds |
Sub-minute or simple intervals (e.g. every 30s, every 5min) |
| Cron | cron_expr |
Calendar-based schedules (e.g. weekdays at 9am) |
| One-time | at |
Single future execution (ISO 8601 datetime in UTC) |
Cron expression format
Five fields: MIN HOUR DOM MON DOW
- MIN: 0-59, HOUR: 0-23, DOM: 1-31, MON: 1-12, DOW: 0-6 (0=Sun)
- Wildcards:
*(any),*/5(every 5),1-5(range),1,15(list) - Examples:
*/5 * * * *(every 5 min),0 9 * * 1-5(weekdays 9am),30 18 * * 0(Sun 6:30pm)
Confirmation format
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.
- 10d ago First seen · 67 lines · 10 tokens per session scan A 3318ca47d7f2
cron is a skill published in the GitHub repository crystal-autobot/autobot (45 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 614 once invoked, about $0.0001 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 skills, from other repositories
apple-tools
Reach Apple PIM data (Calendar, Contacts, Reminders, Messages, Location, Maps, Weather) from a pi session via iMCP + pi-mcp-adapter on macOS. Use when the user asks to read/search their Apple Calendar, Contacts, Reminders, iMessages, current Location, Maps, or Weather. Does NOT cover Apple Mail — iMCP exposes no Mail…
kb-setup
Set up, initialize, or configure the local markdown knowledge base for a project. Use when the user says "set up the knowledge base", "init the KB", "configure the markdown KB", "index my docs", "add a doc source to the KB", or wants the project's markdown searchable by kb search. Wraps kb init end-to-end through kb…
kb-search
Search the local markdown knowledge base for facts, prior decisions, definitions, people, error codes, config flags, and how-we-fixed-it notes. ALWAYS search here BEFORE answering a project-specific question from memory, guessing, or asking the user. Use whenever you hit an unknown term, an unfamiliar entity, an error…
workflow-helper
Guidance for creating, managing and executing workflow automations that chain multiple tools and agents together. Use when the user asks about building, listing, running or composing workflows and automated task pipelines.
automations
Create, inspect, edit, archive, delete, run, and search scheduled or executable automation assets.
ask-user
Ask the human structured questions via nui HITL instead of plain chat text.