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 5.5 | $0.00004 | $0.00246 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo ago First seen · 67 lines · 10 tokens per session scan A 3318ca47d7f2
cron is a skill published in the GitHub repository crystal-autobot/autobot (47 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 614 once invoked, about $0.0000 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
apple-tools
Reach Apple PIM data (Calendar, Contacts, Reminders, Messages, Location, Maps, Weather) from a pi session via iMCP + pi's built-in MCP 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…
pi-dashboard-bootstrap
Make sure the local pi-dashboard server is running before any pi-dashboard action. Use FIRST whenever the user mentions the pi dashboard, pi sessions or pi agents, or asks to start/open the dashboard; also when a dashboard call fails with "connection refused".
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…
pi-dashboard-watch
Get notified when a pi session asks a question, changes status (streaming, idle, ended) or is added or removed, instead of polling. Use after pi-dashboard-bootstrap has printed BASE, whenever you start or prompt a pi session and must react to it, or the user asks to watch pi sessions.
rules-to-guards
Rule enforcer that finds which written rules in AGENTS.md, CLAUDE.md, and GEMINI.md a coding agent keeps breaking, counts every violation in recent Claude Code, Codex, Gemini CLI, and OpenCode sessions, and turns each broken rule into a hook that blocks it, tested by replaying the past violations. Use when the user…