text-to-reminders

text-to-reminders is a skill for Claude Code from sam-phinizy/remindctl-mcp. It costs 106 tokens per session (1,147 once invoked), scanned A, original, MIT.

A guide for turning emails, documents, Slack conversations, or other text into Apple Reminders. It extracts explicit tasks, keeps useful context in notes, and identifies stated due dates.

In plain words
What is it for?
Use it to propose reminders from messages or documents, including short titles, detailed notes, grouped related items, and extracted deadlines.
Why use it?
It reduces the work of finding action items in long text and entering them as reminders. It also avoids creating tasks that the text does not clearly request.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the remindctl plugin — 1 skill shipped together

Good fit Use it to propose reminders from messages or documents, including short titles, detailed notes, grouped related items, and extracted deadlines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sam-phinizy/remindctl-mcp/text-to-reminders
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.

Any agent
npx skills add sam-phinizy/remindctl-mcp --skill text-to-reminders
Clone the repo
git clone --depth 1 https://github.com/sam-phinizy/remindctl-mcp

Made for: Claude Code.

Or install remindctl, the plugin that ships this one along with the rest of its 1 skill.

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 text-to-reminders

README.md
[![agentmods](https://agentmods.dev/badge/skills/sam-phinizy/remindctl-mcp/text-to-reminders/github.svg)](https://agentmods.dev/skills/sam-phinizy/remindctl-mcp/text-to-reminders)
Your own site
<a href="https://agentmods.dev/skills/sam-phinizy/remindctl-mcp/text-to-reminders"><img src="https://agentmods.dev/badge/skills/sam-phinizy/remindctl-mcp/text-to-reminders/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.

agentmods 80×15 button for text-to-reminders

Your own site · 80×15
<a href="https://agentmods.dev/skills/sam-phinizy/remindctl-mcp/text-to-reminders"><img src="https://agentmods.dev/badge/skills/sam-phinizy/remindctl-mcp/text-to-reminders.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,147 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00106 $0.01147
Opus 5 $0.00053 $0.00574
Sonnet 5 $0.00021 $0.00229
Haiku 4.5 $0.00011 $0.00115

Measured 11d ago against content hash ead3417186e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

text-to-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 11d 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.

plugin/skills/text-to-reminders/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Text to Reminders

Parse emails, documents, Slack threads, or any block of text into well-structured Apple Reminders — with short titles, full context in notes, and due dates extracted from the text.

Core Principles

Short titles, rich notes. A good reminder title is scannable in a list: "Call Sarah re: contract" not "Call Sarah to discuss the contract renewal terms before the end of Q2". Move all context into the notes field.

Extract, don't invent. Only create reminders for explicit action items or commitments. Don't infer tasks from background context.

Consolidate before creating. Related items belonging to the same project or person should be grouped into one reminder where possible. Five reminders about the same project create noise.

Propose before acting. Always show the proposed reminder list and get confirmation before calling any MCP tools.

Workflow

Step 1: Read the Text Carefully

Scan the full text for:

  • Explicit action items ("please send", "can you", "we need to", "don't forget")
  • Implicit commitments ("I'll follow up", "let's schedule", "we agreed")
  • Deadlines and dates (absolute: "by March 20", relative: "end of week", "before the call")
  • Named owners — only capture items the user is responsible for

Step 2: Extract Raw Action Items

List every candidate action item with:

  • The raw task as stated in the text
  • The deadline or date hint (if any)
  • The relevant context (who asked, what for, why it matters)

Step 3: Consolidate

Apply these consolidation rules:

  • Merge items that are sub-tasks of the same deliverable into one reminder with all steps in the notes
  • Merge follow-ups about the same person/project into one reminder
  • Keep items separate only if they have different owners, hard deadlines, or unrelated scope

Aim for the fewest reminders that cover all action items without losing information.

Step 4: Propose the Reminder List

Present a structured proposal before creating anything. Use this format for each item:

Read the full file on GitHub · 115 lines

Files

What ships with it

1 file 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.

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. 11d ago First seen · 115 lines · 106 tokens per session scan A ead3417186e6

Subscribe to this mod's changes

text-to-reminders is a skill published in the GitHub repository sam-phinizy/remindctl-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 106 tokens to every session and 1,147 once invoked, about $0.0005 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.

Related

Other skills, from other repositories