agentmods.dev

appsnap

appsnap is a skill for Claude Code from Yrzhe/claude-skills. It costs 124 tokens per session (1,568 once invoked), scanned A, original, MIT.

A macOS window capture tool that takes a screenshot of a selected app window and extracts available text from it. It is intended to provide the visible app as context without controlling the app.

In plain words
What is it for?
Use it to read, summarize, or work from the current Mac window, a visible application, or a full scrollable page.
Why use it?
It lets an agent inspect what is currently shown in an app, including content that may not be available through ordinary text access. For canvas-heavy apps, the screenshot may be the main source of information.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the appsnap plugin — 1 skill shipped together

not rated 33repo 3mo ago A scan 124 tokens original MIT

Good fit Use it to read, summarize, or work from the current Mac window, a visible application, or a full scrollable page.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yrzhe/claude-skills/appsnap
View source ↗ Yrzhe/claude-skills
Install

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.

Any agent
npx skills add Yrzhe/claude-skills --skill appsnap
Clone the repo
git clone --depth 1 https://github.com/Yrzhe/claude-skills

Made for: Claude Code.

Or install appsnap, the plugin that ships this one along with the rest of its 1 skill.

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.

agentmods badge for appsnap

README.md
[![agentmods](https://agentmods.dev/badge/skills/yrzhe/claude-skills/appsnap/github.svg)](https://agentmods.dev/skills/yrzhe/claude-skills/appsnap)
Your own site
<a href="https://agentmods.dev/skills/yrzhe/claude-skills/appsnap"><img src="https://agentmods.dev/badge/skills/yrzhe/claude-skills/appsnap/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.

agentmods 80×15 button for appsnap

Your own site · 80×15
<a href="https://agentmods.dev/skills/yrzhe/claude-skills/appsnap"><img src="https://agentmods.dev/badge/skills/yrzhe/claude-skills/appsnap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,568 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00124 $0.01568
Opus 5 $0.00062 $0.00784
Sonnet 5 $0.00025 $0.00314
Haiku 4.5 $0.00012 $0.00157

Measured 11d ago against content hash bf74a1fd7cdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

appsnap 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 11d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (appsnap.sh, scripts/assemble.py, scripts/ax_extract.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/appsnap/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

appsnap

Capture one selected macOS window and return the screenshot plus extracted text as context.

Scope

  • Use local macOS APIs only. Do not use network or model calls inside scripts.
  • Treat the result as passive context. Do not click, type, or control the app.
  • Exception: default auto mode and --fullpage / {"mode":"fullpage"} may be ACTIVE. Auto hover-picks a window and scroll-stitches only when a bounded AX probe finds a scrollable area. --visible forces a passive single visible screenshot.
  • The screenshot is primary context; you (the consuming agent) read it with your own vision. Accessibility (AX) text is supplementary: its unique value is off-screen / not-scrolled-into-view content. Local OCR is OFF by default — your own vision reads a high-res screenshot more accurately than macOS Vision OCR. Only opt into OCR for non-vision / headless consumers.
  • Be honest for canvas-heavy apps (Google Docs, Sheets, Slides, Gmail, many browsers): AX may expose little or no text. In that case assemble.py returns read_image:true and you must read the screenshot for the visible content. Off-screen canvas text is not reachable by anyone unless the app exposes it through AX.

One-time setup

Scripts need macOS PyObjC frameworks. Create a venv and install:

python3 -m venv <skill-dir>/.venv
<skill-dir>/.venv/bin/pip install -r <skill-dir>/requirements.txt

Run every script below with <skill-dir>/.venv/bin/python (not the system python3).

Flow

  1. Check permissions:

    python3 <skill-dir>/scripts/check_permissions.py

    If it exits nonzero, stop and show its one-line stderr guidance.

  2. Capture a window:

    python3 <skill-dir>/scripts/capture.py

    Stdin is optional. Default is {"mode":"auto"}. Use {"mode":"visible"} for hover-pick without scrolling, {"mode":"fullpage"} to force active scroll-stitching, or {"mode":"frontmost"} only when the user explicitly wants the frontmost window.

Read the full file on GitHub · 160 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 11d ago First seen · 160 lines · 124 tokens per session scan A bf74a1fd7cdb

Subscribe to this mod's changes

appsnap is a skill published in the GitHub repository Yrzhe/claude-skills (33 stars, last pushed 3mo ago), licensed MIT. It adds 124 tokens to every session and 1,568 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens