What is hunch-mcp AGENTS.md?

Repository instructions for Hunch, a tool that lets an AI agent read and control Mac applications in the background without taking over the user's screen, mouse, or keyboard.

Use them when setting up Hunch, changing its tools, working with macOS accessibility features, or running its tests.

They document the design constraints and tests needed to preserve background operation and prevent changes from breaking the tool.

How PrithviSeran/hunch-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to PrithviSeran/hunch-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.

Copy the file

curl -O https://raw.githubusercontent.com/PrithviSeran/hunch-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/PrithviSeran/hunch-mcp

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/prithviseran/hunch-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/prithviseran/hunch-mcp/agents-md)

Your own site

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

Per session 4,917 This file is loaded in full into every session.

When invoked 4,917 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	$0.04917	$0.04917
Opus 5.5	$0.01967	$0.01967
Sonnet 5.5	$0.00983	$0.00983
Haiku 4.5	$0.00492	$0.00492

Measured 1mo ago against content hash 6f10cfe45e43, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hunch-mcp 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.

AGENTS.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — working on Hunch

Context for coding agents modifying this repo. (User-facing "how to use Hunch" lives in README.md; this file is "how the code works and how not to break it.")

Hunch drives a real, logged-in Mac for an LLM focus-free — reading and acting on background apps without stealing the user's screen, cursor, or keyboard. That invariant is the product. Most gotchas below exist to protect it.

Branches and commits (atomic, decoupled)

Every feature, bug fix, or patch belongs on its own branch, cut from current main. Do not pile unrelated work onto an existing branch, an in-progress PR, or a dirty working tree that already belongs to something else. If the task changes, start a new branch (a worktree is fine) instead of mixing it in.

One concern per branch. A Safari fix, a Learn feature, a site tweak, and a docs change are four branches — even when they are all "small."
Commits stay atomic. Each commit is one reviewable change: no drive-by refactors, no leftover files from another task, no "and also" in the same snapshot.
Branches stay decoupled. A branch must merge to main on its own. It must not depend on uncommitted files, another in-progress branch, or a checkout that still carries unrelated diffs.
Do not commit Learn / Safari / site / CI / packaging together unless they are the same change. Discovering extra work is a signal to branch, not to widen the diff.

Setup & tests

.venv/bin/python -m pytest tests/          # full suite; needs pyobjc (the venv has it)
.venv/bin/python -m pytest tests/test_smoke.py

Python ≥ 3.11. Depends on pyobjc (AppKit/ApplicationServices/Quartz) — macOS only.
tests/test_smoke.py::test_tool_count asserts exactly 32 MCP tools. Adding/removing a tool means updating that number in the same commit, on purpose.
Tests fake all AX/Quartz calls (monkeypatch), so they run headless with no UI and touch no Keychain. Keep new logic unit-testable this way: put the OS call behind a function you can patch, assert on the decision logic.

Read the full file on GitHub · 256 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.

1mo ago Changed · +7 lines · +128 tokens per session 6f10cfe45e43
1mo ago Changed · +21 lines · +346 tokens per session aac30fd91084
1mo ago Changed · -1 lines · -35 tokens per session 09be32a3d753
2mo ago First seen · 229 lines · 4,478 tokens per session scan A 30ae392dcf0d

Subscribe to this mod's changes

hunch-mcp AGENTS.md is an instructions file published in the GitHub repository PrithviSeran/hunch-mcp (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 4,917 tokens to every session, about $0.0197 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 2026-08-30.

ai-agents automation computer-use macos mcp

hunch-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hunch-mcp AGENTS.mdPrithviSeran/hunch-mcp	Instructions file	23	2d ago	Apache-2.0	A	4,917	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	today	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

hunch-mcp: Instructions file for Codex