Borrowing it
Nothing to install: this file belongs to Lingnik/icloud-reminders-mcp. 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/Lingnik/icloud-reminders-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/Lingnik/icloud-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/lingnik/icloud-reminders-mcp/claude-md)<a href="https://agentmods.dev/instructions/lingnik/icloud-reminders-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lingnik/icloud-reminders-mcp/claude-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/lingnik/icloud-reminders-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lingnik/icloud-reminders-mcp/claude-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 | $0.00544 | $0.00544 |
| Opus 5 | $0.00272 | $0.00272 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
icloud-reminders-mcp CLAUDE.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 9d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
icloud-reminders-mcp — project conventions
Backlog: GitHub issues, always
All backlog items live as GitHub issues on Lingnik/icloud-reminders-mcp —
never TODO comments, never doc lists. When work items, ideas, deferred fixes, or
follow-ups surface, file an issue immediately with gh issue create. Reference
issues in commits (Closes #N / Refs #N). Check gh issue list first.
Secrets
- Never hardcode credentials or write a real
.env. Only.env.exampleis tracked. This repo is public — no real values, list names, or captured account fixtures ever get committed. - Runtime secrets come from 1Password:
op run --env-file ~/.secrets -- …. The refs areICLOUD_USERNAME/ICLOUD_APP_PASSWORD→op://kalipi-claude/icloud-reminders-mcp/{username,password}.
Architecture
config.py— env parsing, allowlist, flags. No network.vtodo.py— pure VTODO⇄dict mapping + construction. No network. Updates mutate the parsed component in place; never rebuild a VTODO from JSON, so unknown properties (RRULE/VALARM/RELATED-TO/X-APPLE-*) are preserved.caldav_client.py— all network: discovery, CRUD, ETag concurrency, backoff.server.py— FastMCP tool registration (stdio).errors.py— typed error hierarchy.
Testing
- Everything under
tests/is network-free (pure logic + a fake CalDAV layer). Fixtures are synthetic — never from a real account. scripts/doctor.pyis the only thing that hits the real account. Never run it in CI.- Before pushing:
uv run ruff check .anduv run pytestmust pass.
iCloud gotchas (hard-won; keep in mind)
- Discover from the root; never hardcode the
pNN-caldav.icloud.comshard. - Only non-"upgraded" (pre-CloudKit) reminder lists sync via CalDAV; some accounts have none.
- iCloud may normalize/drop properties on write and hides completed todos from
the default query (
include_completed=Trueto see them). - Keep
create_list(MKCALENDAR) out until round-trip fidelity is proven — CalDAV-created lists may not surface in the iOS app.
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.
- 9d ago First seen · 46 lines · 544 tokens per session scan A 8834bee801d2
icloud-reminders-mcp CLAUDE.md is an instructions file published in the GitHub repository Lingnik/icloud-reminders-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 544 tokens to every session, about $0.0027 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.
Other instructions, from other repositories
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.
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 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).
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).
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.
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.