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/smughead/loupe/claude-mdgit clone --depth 1 https://github.com/smughead/LoupeWrote 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/smughead/loupe/claude-md)<a href="https://agentmods.dev/instructions/smughead/loupe/claude-md"><img src="https://agentmods.dev/badge/instructions/smughead/loupe/claude-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 5.1 | $0.00709 | $0.00709 |
| Opus 5 | $0.00354 | $0.00354 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
Loupe 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 6d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build Commands
# Build the app (from project root)
xcodebuild -workspace Loupe.xcworkspace -scheme Loupe -configuration Debug build
# Run all tests (unit + UI)
xcodebuild -workspace Loupe.xcworkspace -scheme Loupe -configuration Debug test
# Run only SPM package unit tests
xcodebuild -workspace Loupe.xcworkspace -scheme LoupeFeature test
# Run only UI tests
xcodebuild -workspace Loupe.xcworkspace -scheme Loupe -only-testing:LoupeUITests test
# Clean build
xcodebuild -workspace Loupe.xcworkspace -scheme Loupe clean
Open Loupe.xcworkspace in Xcode (not the .xcodeproj).
Architecture
This is a macOS accessibility inspection app using a Workspace + SPM Package architecture:
Loupe.xcworkspace
├── Loupe.xcodeproj # App shell (minimal - just imports LoupeFeature)
│ └── Loupe/LoupeApp.swift # @main entry point
└── LoupePackage # SPM package (all feature code lives here)
└── Sources/LoupeFeature/
├── ContentView.swift # Main UI (NavigationSplitView)
├── Models/AXElementInfo.swift # Accessibility element data
├── Services/AccessibilityInspector.swift # macOS Accessibility API wrapper
└── Views/OverlayWindowController.swift # Transparent inspection overlay
Core Components
AccessibilityInspector (@Observable, @MainActor): Wraps macOS Accessibility APIs (AXUIElement* functions). Manages permission checking, app enumeration, and element inspection at screen coordinates.
OverlayWindowController: Creates a transparent, borderless NSWindow that floats above the target app. Uses timer-based position tracking and a custom NSView for mouse event capture. Draws green dashed highlight rectangles around hovered elements.
AXElementInfo: Value type holding extracted accessibility metadata (role, identifier, title, value, frame, hierarchy path). Includes searchPatterns property that generates regex patterns for AI agents to locate elements in code.
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.
- 6d ago First seen · 80 lines · 709 tokens per session scan A 93a62b154e9b
Loupe CLAUDE.md is an instructions file published in the GitHub repository smughead/Loupe (111 stars, last pushed 1mo ago), licensed MIT. It adds 709 tokens to every session, about $0.0035 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
barkeep AGENTS.md
AGENTS.md instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.
barkeep CLAUDE.md
Claude Code instructions for iannuttall/barkeep, a project described as: Manage hidden macOS menu bar items from one place.
Applite CLAUDE.md
Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.
Peekaboo AGENTS.md
AGENTS.md instructions for openclaw/Peekaboo, covering repository guidelines, start here, project structure & modules, build, test, and development commands and coding style & naming conventions.
scarf AGENTS.md
AGENTS.md instructions for awizemann/scarf: This repo carries its own agent memory — plain files in git, served by the in-repo memophant-mcp MCP server, managed by the Memophant macOS app. It works the same for every agent (Claude Code, Codex, Cursor, Gemini, Copilot). This block is regenerated between the memophant…
palmier-pro AGENTS.md
AGENTS.md instructions for palmier-io/palmier-pro, covering palmierpro, build, agents, engineering approach and code style.