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 CraftOS-dev/CraftBot --skill remindmegit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWrote 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/craftos-dev/craftbot/remindme)<a href="https://agentmods.dev/skills/craftos-dev/craftbot/remindme"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/remindme/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/craftos-dev/craftbot/remindme"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/remindme.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 | $0.00020 | $0.03188 |
| Opus 5.5 | $0.00008 | $0.01275 |
| Sonnet 5.5 | $0.00004 | $0.00638 |
| Haiku 4.5 | $0.00002 | $0.00319 |
Grade A, and why
remindme 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remind Me v2
Set reminders on any channel using natural language. No setup. No dependencies.
Usage
/remindme drink water in 10 minutes
/remindme standup tomorrow at 9am
/remindme call mom next monday at 6pm
/remindme in 2 hours turn off oven
/remindme check deployment in 30s
/remindme every day at 9am standup
/remindme every friday at 5pm week recap
/remindme drink water in 10 minutes on telegram
/remindme standup tomorrow at 9am on discord
/remindme list
/remindme cancel <jobId>
Agent Instructions
When the user triggers /remindme, determine the intent:
- list → call
cron.listand show active reminder jobs. - cancel / delete / remove
<jobId>→ callcron.removewith that jobId. - everything else → create a new reminder (steps below).
Step 1: Parse the Input (Structured Pipeline)
Extract three things: WHAT (the message), WHEN (the time), RECURRENCE (one-shot or recurring).
Follow this decision tree in order — stop at the first match:
Layer 1: Pattern Matching (works on any model)
Scan the input for these patterns. Match top-to-bottom, first match wins for WHEN:
Relative durations — look for in <number> <unit>:
| Pattern | Duration |
|---|---|
in Ns, in N seconds, in N sec |
N seconds |
in Nm, in N min, in N minutes |
N minutes |
in Nh, in N hours, in N hr |
N hours |
in Nd, in N days |
N * 24 hours |
in Nw, in N weeks |
N * 7 days |
Absolute clock times — look for at <time>:
| Pattern | Meaning |
|---|---|
at HH:MM, at H:MMam/pm |
Today at that time (or tomorrow if past) |
at Ham/pm, at HH |
Today at that hour |
Named days — look for tomorrow, next <day>, on <day>:
| Pattern | Meaning |
|---|---|
tomorrow |
Next calendar day, default 9am |
tonight |
Today at 8pm (or now+1h if past 8pm) |
next monday..sunday |
The coming occurrence of that weekday, default 9am |
on <day> |
Same as next <day> |
Recurring — look for every <pattern>:
| Pattern | Cron/Interval |
|---|---|
every Nm/Nh/Nd |
kind: "every", everyMs: N * unit_ms |
every day at <time> |
kind: "cron", expr: "M H * * *" |
every <weekday> at <time> |
kind: "cron", expr: "M H * * DOW" |
every weekday at <time> |
kind: "cron", expr: "M H * * 1-5" |
every weekend at <time> |
kind: "cron", expr: "M H * * 0,6" |
every hour |
kind: "every", everyMs: 3600000 |
What ships with it
2 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.
- 1mo ago First seen · 313 lines · 20 tokens per session scan A 0563fda11bd1
remindme is a skill published in the GitHub repository CraftOS-dev/CraftBot (396 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 3,188 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
community
Use when building or running a persistent two-way community space — Discord, Telegram, Circle: platform choice, structure, onboarding, native→bot→human moderation, rituals, growth loops, health metrics. NOT churn of paying product customers (that is retention), NOT broadcast email (that is newsletter), NOT one live…
frontmcp-channels
Use when pushing real-time notifications or events into Claude Code (or another MCP client) sessions, or building two-way chat bridges. Covers channel source types: incoming webhooks (such as GitHub), app error events, agent-completion and job-completion alerts, service connectors, file watchers, and replay buffers…
reminder
A personal reminder tool for the current chat. It can create, list, and cancel reminders that send a message back to this conversation.
telegram-chat-admin
A Telegram group administration tool for checking members and administrators before changing group settings.
holix-cron
Schedule recurring agent tasks via Holix built-in gateway cron (not crontab or custom scripts).
telegram-messages
A Telegram messaging tool for creating polls, adding reactions, and sending stickers.