reminder-format

reminder-format is a skill for Claude Code, Codex from Rustam-Z/hamroh. It costs 82 tokens per session (492 once invoked), scanned A, original, MIT.

A command-line interface for Beeper Desktop, which brings conversations from services such as Telegram, WhatsApp, Slack, and iMessage into one application.

In plain words
What is it for?
Use it to check authentication, list accounts and chats, search messages, filter inboxes, and send messages.
Why use it?
It lets you manage connected messaging accounts and conversations from a terminal instead of switching between separate messaging apps.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/rustam-z/hamroh/reminder-format
Any agent
npx skills add Rustam-Z/hamroh --skill reminder-format
Clone the repo
git clone --depth 1 https://github.com/Rustam-Z/hamroh

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 reminder-format

README.md
[![agentmods](https://agentmods.dev/badge/skills/rustam-z/hamroh/reminder-format.svg)](https://agentmods.dev/skills/rustam-z/hamroh/reminder-format)
Your own site
<a href="https://agentmods.dev/skills/rustam-z/hamroh/reminder-format"><img src="https://agentmods.dev/badge/skills/rustam-z/hamroh/reminder-format.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 492 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 5.1 $0.00082 $0.00492
Opus 5 $0.00041 $0.00246
Sonnet 5 $0.00016 $0.00098
Haiku 4.5 $0.00008 $0.00049

Measured 6d ago against content hash fcb775ece125, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reminder-format 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 6d 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.

skills/reminder-format/SKILL.md · 48 lines

What it actually says

Skill: reminder-format

Reference skill (no <reminder> envelope required). Read it before calling reminder_set — and again before editing a reminder (which means reminder_cancel + a fresh reminder_set). The format applies to the text argument; cron and trigger_at are unaffected.

The reminder text is a self-prompt: when the timer fires, this exact string lands in your input as <reminder>…</reminder> and re-orients a fresh turn. Past-you is briefing future-you. Write it that way.

The three rules

  1. Opening line. The first line of text is exactly <THIS IS A REMINDER> — literal, including the angle brackets and uppercase. It anchors future-you immediately, before any envelope parsing.
  2. Goal line. One short sentence right after the opener, prefixed Goal:. State why this reminder exists — the outcome past-you wanted.
  3. Steps. A numbered list (1., 2., …) of the concrete actions future-you should take when it fires. One line per step, imperative voice ("send X", "check Y", "DM the owner if Z"). No nesting, no sub-bullets.

Example

<THIS IS A REMINDER>
Goal: follow up with Alice on the GitLab MR she opened yesterday.
1. Read the MR status via WebFetch.
2. If still open, DM Alice asking if she needs review help.
3. If merged, send a thumbs-up reaction in the original chat.

Don'ts

  • No markdown headers, no prose paragraphs in place of steps.
  • Don't skip the opener even for one-liners — the literal marker is the cue.
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. 6d ago First seen · 48 lines · 82 tokens per session scan A fcb775ece125

Subscribe to this mod's changes

reminder-format is a skill published in the GitHub repository Rustam-Z/hamroh (54 stars, last pushed 12d ago), licensed MIT. It adds 82 tokens to every session and 492 once invoked, about $0.0004 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.