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 instructions/mhtb32/reminders-mcp/claude-mdgit clone --depth 1 https://github.com/mhtb32/reminders-mcpWrote 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/instructions/mhtb32/reminders-mcp/claude-md)<a href="https://agentmods.dev/instructions/mhtb32/reminders-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mhtb32/reminders-mcp/claude-md.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 5.1 | $0.00467 | $0.00467 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
reminders-mcp CLAUDE.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Tests mock `subprocess.run` to avoid needing the Reminders app or macOS. All AppleScript calls go through `_run_applescript()` in `reminders.py`, which is the right place to patch. What it actually says
reminders-mcp
MCP server for macOS Reminders app, written in Python using FastMCP.
Commands
uv sync # install dependencies
uv run reminders-mcp # run the server
uv run pytest tests/ -v # run tests
Architecture
src/reminders_mcp/reminders.py— all macOS Reminders access via AppleScript (osascript)src/reminders_mcp/server.py— MCP tool definitions using FastMCP
Tools
| Tool | Description |
|---|---|
list_reminder_lists |
Get all list names |
list_reminders |
List reminders with name, due date, notes, completed; optional list filter |
create_reminder |
Create with optional due date and notes |
update_reminder |
Update title, notes, and/or due date of an existing reminder |
complete_reminder |
Mark as completed |
delete_reminder |
Delete permanently |
list_reminders returns notes as a string (multiline notes preserved) or null.
Key Constraints
- macOS only — everything goes through AppleScript; no cross-platform support
- Sections not supported — macOS Reminders sections are not exposed via AppleScript or EventKit's public API
- No direct DB access — the Reminders SQLite store is behind sandbox restrictions
Testing
Tests mock subprocess.run to avoid needing the Reminders app or macOS. All AppleScript calls go through _run_applescript() in reminders.py, which is the right place to patch.
with patch("subprocess.run", return_value=mock_run("ok")):
...
CI runs on macos-latest via GitHub Actions on every push and PR to main.
Dependency Management
Uses uv. Do not use pip directly. To add a package: uv add <package>. Dev dependencies: uv add --dev <package>.
Claude Desktop Config
Server is registered in ~/Library/Application Support/Claude/claude_desktop_config.json under the key 🖊️ reminders.
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.
- 5d ago First seen · 55 lines · 467 tokens per session scan A f06fa4c249c1
reminders-mcp CLAUDE.md is an instructions file published in the GitHub repository mhtb32/reminders-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 467 tokens to every session, about $0.0023 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.