Borrowing it
Nothing to install: this file belongs to rex/mcp-apple-reminders. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rex/mcp-apple-reminders/main/AGENTS.mdgit clone --depth 1 https://github.com/rex/mcp-apple-remindersWrote 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/rex/mcp-apple-reminders/agents-md)<a href="https://agentmods.dev/instructions/rex/mcp-apple-reminders/agents-md"><img src="https://agentmods.dev/badge/instructions/rex/mcp-apple-reminders/agents-md/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.
<a href="https://agentmods.dev/instructions/rex/mcp-apple-reminders/agents-md"><img src="https://agentmods.dev/badge/instructions/rex/mcp-apple-reminders/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03546 | $0.03546 |
| Opus 5.5 | $0.01418 | $0.01418 |
| Sonnet 5.5 | $0.00709 | $0.00709 |
| Haiku 4.5 | $0.00355 | $0.00355 |
Grade A, and why
mcp-apple-reminders AGENTS.md 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
1. Project snapshot
- What: macOS-only MCP server exposing Apple Reminders (EventKit + private ReminderKit) to Claude Code, Codex, and Claude Desktop.
- Runtime: Python 3.10+ (repo venv runs 3.13.5 from miniconda). MCP SDK 1.27+ (FastMCP) + PyObjC. Three-tier native layer at
src/mcp_apple_reminders/_native/(renamed fromlibs/pyremindkit/in slice 0.2). - Platform: macOS only — depends on
EventKit/ReminderKitand a granted Reminders permission on the interpreter binary. - Owner: @pierce (single-author repo as of 2026-05).
- Non-goals: cross-platform support, reminder UI (use Reminders.app), iCloud sync logic (macOS handles it).
2. Setup
./install.sh # creates ./venv, installs editable pkg + deps, builds native helpers
./venv/bin/python3 verify_setup.py # preflight: interpreter, deps, perms, client configs
Grant Reminders permission on first launch — approve the macOS dialog when verify_setup.py runs, OR run ./shim_mcp.sh once and approve. Permission is per-binary; the conda Python interpreter must be the one approved.
3. Commands the agent MUST run before declaring done
ruff check src/ tests/black --check src/ tests/./venv/bin/python -m pytest tests/test_mcp_tools.py tests/test_workflow_tools.py tests/test_e2e.py— explicit paths (ormake test-actual)make check-architecture(line-limit gate: hard cap 400 lines/file)make bump-patch(or minor/major) before commit —bump_required_per_commit: true
4. Repo layout
src/mcp_apple_reminders/ FastMCP server (server.py) + lifespan.py + models.py + formatting.py
src/mcp_apple_reminders/tools/ 17 @mcp.tool modules: calendars, reminders, completion, queries,
workflow, groups, alarms, bulk, sections, smartlists, appearance,
templates, flags, attachments, grocery, agents, sampling (58 tools)
src/mcp_apple_reminders/resources/ @mcp.resource SQLite views (e.g. agents://current/{project})
src/mcp_apple_reminders/prompts/ @mcp.prompt canned workflows
src/mcp_apple_reminders/_native/ Three-tier native layer: sqlite.py (+ _sqlite_helpers) = reads;
eventkit.py = Swift EventKit helper; reminderkit.py +
reminderkit_actions.py = Obj-C ReminderKit (private) helper;
legacy PyObjC wrapper (core, _internal, calendars, models); bulk.py
src/mcp_apple_reminders/_native/bin/ Compiled rem_eventkit + rem_reminderkit (from _native/src/
*.swift / *.m; build with `make build-native`)
scripts/ Gate scripts (bump_version, check_architecture, check_module_rules, …)
tests/ Test suite (test_*.py) + tests/_support/ (TestResults harness, cleanup)
docs/ MAP.md, TOOLS.md, SQLITE_SCHEMA.md, SECURITY-REVIEW.md, adr/, audits/
verify_setup.py Install + permission + client-config verification
install.sh, shim_mcp.sh Bootstrap + first-run permission-prompt shim
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.
- 1mo ago Changed · -1 lines · -93 tokens per session 23c5872c3790
- 1mo ago First seen · 102 lines · 3,639 tokens per session scan A 75a5374dd1a4
mcp-apple-reminders AGENTS.md is an instructions file published in the GitHub repository rex/mcp-apple-reminders (3 stars, last pushed 25d ago), licensed MIT. It adds 3,546 tokens to every session, about $0.0142 per session on Opus 5.5. 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.