Borrowing it
Nothing to install: this file belongs to abhinavag-svg/apple-ecosystem-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/abhinavag-svg/apple-ecosystem-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/abhinavag-svg/apple-ecosystem-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/abhinavag-svg/apple-ecosystem-mcp/claude-md)<a href="https://agentmods.dev/instructions/abhinavag-svg/apple-ecosystem-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/abhinavag-svg/apple-ecosystem-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/abhinavag-svg/apple-ecosystem-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/abhinavag-svg/apple-ecosystem-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 | $0.02643 | $0.02643 |
| Opus 5 | $0.01321 | $0.01321 |
| Sonnet 5 | $0.00529 | $0.00529 |
| Haiku 4.5 | $0.00264 | $0.00264 |
Grade D, and why
apple-ecosystem-mcp CLAUDE.md scanned grade D with 3 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **[.claude/settings.local.json](./.claude/settings.local.json)** — Pre-approved tools, agent teams enabled Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf mcpb && mkdir -p mcpb/contents Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Threading:** Module-level `threading.Lock` serializes every `subprocess.run()` call — AppleScript against GUI is not thread-safe How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Ecosystem MCP — Internal Engineering Guide
This is an internal implementation reference for maintainers and contributors. It is not the best public entry point for understanding the product. For the project narrative, use README.md and the docs set under docs/.
This file exists to capture engineering contracts, release discipline, and contributor expectations for the current codebase.
Critical Contracts
These are the working constraints for this repo. Breaking them tends to cause tool registration failures, permission errors, data-shape drift, or security regressions.
AppleScript Bridge
- argv pattern only: Always pass user data as positional arguments:
osascript -e 'on run argv...end run' -- "$arg1" "$arg2" - Never interpolate: Do not use
shlexor string interpolation into AppleScript source - Serialization: All structured returns must be JSON strings, parsed with
json.loads() - Dates: ISO 8601 format via
«class isot» as stringin AppleScript - Threading: Module-level
threading.Lockserializes everysubprocess.run()call — AppleScript against GUI is not thread-safe
Canonical Identifiers
- Mail: RFC Message-ID (
id of messagein AppleScript) - Calendar: iCalendar UID (
uid of event) - Contacts: vCard UUID (
id of person) - Reminders: UUID (
id of reminder) - All tools must target by ID/UID, never by localized display name
Localization Rule
- Mailbox/calendar/list names ARE locale-specific (English, French, etc. have different names)
- Never hardcode display names like
"Calendar","INBOX","Reminders" - Always use persistent IDs or return
{name, id, account_name}so callers useidnotname - Defaults:
calendar_uid=Nonemeans "all calendars";mailbox_id=Nonemeans "all mailboxes"
Error Handling
- Never leak stderr:
stderrmay contain email subjects, contact names, file paths - Raise
RuntimeError(f"AppleScript failed (exit {code})")only; log stderr to DEBUG file logger - FastMCP surfaces
RuntimeErroras tool error automatically — don't importMcpError
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.
- 11d ago First seen · 234 lines · 2,643 tokens per session scan D ce50b8fa8f84
apple-ecosystem-mcp CLAUDE.md is an instructions file published in the GitHub repository abhinavag-svg/apple-ecosystem-mcp (7 stars, last pushed 2mo ago), licensed MIT. It adds 2,643 tokens to every session, about $0.0132 per session on Opus 5. A static security scan graded it D with 3 findings (reads agent configuration directories, recursive force delete, 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
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).
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.
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 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).