What is macos-mcp-tools AGENTS.md?

Repository instructions for working with macOS MCP tools, including project structure, commands, state-changing actions, and testing limits.

They are for guiding agents that inspect or operate macOS tools while respecting the project's side-effect and testing rules.

They tell an agent how this repository expects macOS tool use and testing to be handled.

How HachiTogo/macos-mcp-tools configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to HachiTogo/macos-mcp-tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/HachiTogo/macos-mcp-tools/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/HachiTogo/macos-mcp-tools

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hachitogo/macos-mcp-tools/agents-md/github.svg)](https://agentmods.dev/instructions/hachitogo/macos-mcp-tools/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hachitogo/macos-mcp-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/hachitogo/macos-mcp-tools/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hachitogo/macos-mcp-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/hachitogo/macos-mcp-tools/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 896 This file is loaded in full into every session.

When invoked 896 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00896	$0.00896
Opus 5.5	$0.00358	$0.00358
Sonnet 5.5	$0.00179	$0.00179
Haiku 4.5	$0.00090	$0.00090

Measured 24d ago against content hash 1ce1f2382572, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

macos-mcp-tools 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 24d 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.

AGENTS.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Commands

Bun on macOS only. Entrypoint: bun run src/cli.ts <mail|contacts|notes|memory|messages|events|reminders>.
bun test (single file: bun test src/servers/mail.test.ts), bun run typecheck, bun run lint (Biome; bun run format fixes).
Opt-in: bun run test:integration; test:integration:apps hits live Apple apps.
bun run build:swift builds the untracked bin/EventKitCLI (needs swiftc); events, reminders and bun test require it.
Do not invent extra verification steps. CI builds the binary, then runs exactly bun run lint, bun test, bun run typecheck and bun run test:integration.

Structure

Single package. src/cli.ts is the only entrypoint and dynamically imports one stdio MCP server per subcommand.
Servers: src/servers/<name>.ts registers tools; mail, memory and reminders keep their logic in src/servers/<name>/.
Shared JXA helper: src/lib/jxa.ts. EventKit bridge: src/lib/eventkit/, which shells out to bin/EventKitCLI.
package.json files globs src/**/*.ts; src/package-manifest.test.ts checks that new files ship.

Development Guidance

Every change lands through a pull request against main. Never push directly to main.
Each PR or stack gets its own branch off main. Do not reuse a branch across unrelated changes.
Do not bump package.json; add CHANGELOG entries under ## [Unreleased]. make release VERSION=x.y.z opens a PR that promotes them and bumps once, sized to everything in it: patch for fixes, minor for features or pre-1.0 breaks, major past 1.0. main's version always equals what npm serves.
Keep each PR near 300 lines of code, excluding comments and tests. One reviewable concern per PR.
Larger work splits into stacked PRs with gh stack (see gh stack --help): gh stack init, commit a slice, gh stack add <branch>, gh stack submit, gh stack sync after merges. Each slice must pass CI and stand alone.
Style: TypeScript strict, ESM, no semicolons, enforced by Biome. Run bun run format before committing.
Add or update unit tests for helper logic you touch. Update README.md when tool names or arguments change.
Commit messages use conventional prefixes (feat:, fix:, docs:).

Read the full file on GitHub · 42 lines

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.

24d ago Changed · +1 lines · -57 tokens per session 1ce1f2382572
27d ago Changed f3aa2184e956
29d ago Changed · +5 tokens per session ece5f6d42834
1mo ago Changed · +7 tokens per session 00ea595985ad
1mo ago Changed · +16 tokens per session 8db015cd854d
1mo ago Changed · +46 tokens per session 252245e7b425
1mo ago Changed · +14 lines · +394 tokens per session db8ac6e0b02b
2mo ago First seen · 27 lines · 485 tokens per session scan A 9c2b5a1e1363

Subscribe to this mod's changes

macos-mcp-tools AGENTS.md is an instructions file published in the GitHub repository HachiTogo/macos-mcp-tools (0 stars, last pushed 23d ago), licensed MIT. It adds 896 tokens to every session, about $0.0036 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.

macos-mcp-tools AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
macos-mcp-tools AGENTS.mdHachiTogo/macos-mcp-tools	Instructions file	0	23d ago	MIT	A	896	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

macos-mcp-tools: Instructions file for Codex