reminders

reminders is a skill for Claude Code, Codex from unclutter-pro/atlas. It costs 34 tokens per session (2,257 once invoked), scanned A, original, MIT.

A scheduling tool for starting a coding-agent session at a chosen time, after an email reply, or when a shell command reports success. A recurring reminder can run the same check repeatedly.

In plain words
What is it for?
It is for reminders, follow-ups, deployment checks, CI checks, and other tasks triggered by time, replies, or script conditions.
Why use it?
It removes the need to keep a session open or repeatedly check whether a deadline, reply, deployment, or file has arrived.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/unclutter-pro/atlas/reminders
Any agent
npx skills add unclutter-pro/atlas --skill reminders
Clone the repo
git clone --depth 1 https://github.com/unclutter-pro/atlas

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for reminders

README.md
[![agentmods](https://agentmods.dev/badge/skills/unclutter-pro/atlas/reminders.svg)](https://agentmods.dev/skills/unclutter-pro/atlas/reminders)
Your own site
<a href="https://agentmods.dev/skills/unclutter-pro/atlas/reminders"><img src="https://agentmods.dev/badge/skills/unclutter-pro/atlas/reminders.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,257 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.02257
Opus 5 $0.00017 $0.01128
Sonnet 5 $0.00007 $0.00451
Haiku 4.5 $0.00003 $0.00226

Measured 5d ago against content hash 6cb5372cefff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 5d 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.

app/defaults/skills/reminders/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reminders

Three trigger types — pick the one that matches what you're actually waiting on:

Trigger Use when
--at=<time> Wall-clock deadline. "Remind me at 14:00", "follow up in 30 minutes".
--when-reply-to=<thread-id> Waiting on a human / external system to reply by email. Most stakeholder loops use this.
--when-script-ok=<cmd> Waiting on an external system you can poll cheaply (deploys, CI builds, file landings, status APIs).

Each reminder runs a Claude session with the given prompt when it fires. Reminders can be one-shot or recurring; session routing picks up the originating channel automatically.

CLI Commands

Add a time-based reminder

reminder add --title="Standup" --at="2026-03-08 09:00" --prompt="Send the daily standup summary"
reminder add --title="Deploy check" --at="+2h" --prompt="Verify the rollout completed"
reminder add --title="Quick nudge" --at="+30m" --prompt="Ping Max about the proposal"

Add a recurring reminder (still --at-based)

reminder add --title="Build watch" --at="+5h" --recurring=5h --prompt="Review CI status"

--recurring is only supported with --at. See the Recurring Reminders section below.

Wait for an email reply

# Most common: wait forever for a reply (real humans take days)
reminder add --title="Müller OK" \
  --when-reply-to="thread-abc123" \
  --prompt="Müller hat geantwortet — gleich abarbeiten"

# Restrict to a specific sender on the thread (substring match on the From: address)
reminder add --title="Müller OK" \
  --when-reply-to="thread-abc123" \
  --from="[email protected]" \
  --prompt="Müller hat geantwortet — gleich abarbeiten"

# Safety net: give up after two weeks if nothing arrives
reminder add --title="Müller OK" \
  --when-reply-to="thread-abc123" \
  --timeout="+14d" \
  --prompt="Müller hat geantwortet (oder Timeout) — entscheiden"

Use email threads to find the right thread-id. When a reply arrives, the reminder fires at the next check tick (every minute by default).

Read the full file on GitHub · 158 lines

Changes

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.

  1. 5d ago First seen · 158 lines · 34 tokens per session scan A 6cb5372cefff

Subscribe to this mod's changes

reminders is a skill published in the GitHub repository unclutter-pro/atlas (2 stars, last pushed 16d ago), licensed MIT. It adds 34 tokens to every session and 2,257 once invoked, about $0.0002 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 2026-08-31.