Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/prithviseran/hunch-mcp/agents-mdgit clone --depth 1 https://github.com/PrithviSeran/hunch-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/prithviseran/hunch-mcp/agents-md)<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="Measured on agentmods" 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 | $0.04478 | $0.04478 |
| Opus 5 | $0.02239 | $0.02239 |
| Sonnet 5 | $0.00896 | $0.00896 |
| Haiku 4.5 | $0.00448 | $0.00448 |
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 5d 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 — 229 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.
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_countasserts exactly 29 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.
Architecture — one engine, three faces
The SDK is the product; everything else is an app built on it.
sdk.py—Hunch, the developer-facing SDK object (instance-owned policy, auth injectionApiKey/OAuthToken/"none",app_idnamespacing, notify handler).server.py— the MCP server, an app built ON the SDK (the first one). 29@mcp.tool()functions each call_run(name, ...)→agent._dispatch_core. Its only "personal machine" specialness is constructor args (policy="personal", Hunch branding).agent.py— the agent loop (Agent.run), two backends: api (anthropic, metered) and subscription (claude-agent-sdk, the user's Claude sign-in).backend="auto"picks by ambient credentials._dispatch_core(mac, name, args)is the single tool-execution engine shared by both the server and the agent loop — expected Hunch exceptions become plain content strings so the model can adapt; only unexpected ones setis_error.local_mac.py— the macOS backend:MacSession(AX perception + action primitives) andLocalComputer(exposes snapshot/act/screenshot to the loop). The biggest, most delicate file.ax_tree_mac.py— low-level AX helpers (get_attr/get_attrs,get_window,get_actions,values_to_bounds, tree walk). One IPC round-trip matters here; huge trees (Mail inbox = one AXRow per email) make naive per-attribute reads take minutes.cdp.py— the web/Electron backend (Chrome DevTools Protocol), background-driven.gate.py/policy.py— consent.Gate.front_gate/confirm_dialog;confirm="off"orHUNCH_NO_INTERNAL_GATE=1env = auto-approve (host owns permissions, e.g. the desktop app).os_ops.py(files/clipboard/AppleScript),creds.py/auth.py(Keychain),notify.py,errors.py,playbook.py(HUNCH_PLAYBOOK;server.pyserves it asFastMCP(instructions=…)so every connected client receives it. Change the model-facing contract here, not the tool docstrings.),cli.py.
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.
- 5d ago First seen · 229 lines · 4,478 tokens per session scan A 30ae392dcf0d
hunch-mcp AGENTS.md is an instructions file published in the GitHub repository PrithviSeran/hunch-mcp (19 stars, last pushed 2d ago), licensed Apache-2.0. It adds 4,478 tokens to every session, about $0.0224 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 2026-08-30.
Other instructions, from other repositories
MacOS-MCP CLAUDE.md
Claude Code instructions for CursorTouch/MacOS-MCP, covering macos-mcp: project documentation for claude, project overview, tech stack, architecture and entry point (src/macosmcp/main.py).
codex-computer-use-mcp AGENTS.md
Instructions for tmustier/codex-computer-use-mcp, covering repository guidance, scope, review and verification.
dsh-record-replay AGENTS.md
Instructions for humblebanana/dsh-record-replay, covering agents, build and test, hard rules and layout.
OpenAra AGENTS.md
Instructions for Aradotso/OpenAra, covering openara agent guide, read first, working rules and where things live.
silenthand-cua AGENTS.md
AGENTS.md instructions for edosulai/silenthand-cua, covering graphify and public repo hygiene.
silenthand-cua CLAUDE.md
Claude Code instructions for edosulai/silenthand-cua, covering graphify and public repo hygiene.