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 agentmods add skills/diillson/chatcli/remindersnpx skills add diillson/chatcli --skill remindersgit clone --depth 1 https://github.com/diillson/chatcliWrote 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/diillson/chatcli/reminders)<a href="https://agentmods.dev/skills/diillson/chatcli/reminders"><img src="https://agentmods.dev/badge/skills/diillson/chatcli/reminders.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.00920 |
| Opus 5 | $0.00035 | $0.00460 |
| Sonnet 5 | $0.00014 | $0.00184 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
reminders 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 yesterday.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reminders
Two distinct things hide behind "remind me" — pick the right one:
- A reminder/to-do in the user's reminders app (persists in their ecosystem, syncs to phone). Use native tooling.
- A timed nudge from ChatCLI itself — "ping me in 2h", "message me tomorrow at 9 to do X".
Use ChatCLI's built-in
@scheduler(+@sendto deliver), no external app needed. This is the self-contained path and works on every OS.
If the user is talking to ChatCLI over a gateway (Telegram/WhatsApp) and wants to be messaged, prefer path 2. If they want it in Apple/Google Reminders, use path 1.
Path 1 — Native reminders app (OS-specific)
ChatCLI is multi-OS — pick by platform:
- macOS → AppleScript
Reminders.app(no install):
List open items:osascript -e 'tell application "Reminders" to make new reminder with properties {name:"Call the dentist", due date:(date "2026-06-04 09:00")}'osascript -e 'tell application "Reminders" to get name of (reminders whose completed is false)' - Windows → a scheduled Toast reminder via PowerShell
ScheduledTasks, or simply use Path 2 (the ChatCLI scheduler) which is cleaner and OS-agnostic. Detect withGet-Command remind -ErrorAction SilentlyContinue. - Linux with
remind(1)installed (command -v remind) → append to~/.remindersand query withremind ~/.reminders. If nothing suitable is installed, fall back to Path 2.
When unsure what's installed, prefer Path 2 — it needs no external app and works identically on Windows, macOS, and Linux.
Path 2 — ChatCLI scheduler (timed nudge, any OS)
Schedule a job that fires later and delivers a message. Resolve "now" first if the delay is
relative — macOS / Linux: date '+%Y-%m-%d %H:%M %Z'; Windows:
Get-Date -Format "yyyy-MM-dd HH:mm zzz". Then use @scheduler to register the job, pairing it with @send so the reminder reaches the
user on their channel. Consult the @scheduler tool schema for the exact when/every/payload
fields (one-shot vs recurring), and confirm the resolved absolute time back to the user.
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.
- yesterday First seen · 71 lines · 70 tokens per session scan A 8093c00fd46c
reminders is a skill published in the GitHub repository diillson/chatcli (89 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 920 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
coding
编写并运行 Python 代码，验证脚本逻辑和输出。.
data_analysis
基于已确认数据执行可审计的数学计算和描述统计。.
aidd-dev:00:sdlc
Pure orchestrator for the full AIDD development flow. Use when a human (or Gardener) needs to take a free-form request from idea to shipped code, end-to-end. Coordinates spec generation, planning, implementation, and review by composing other skills and agents. Holds no business logic of its own — every step is…