A macOS automation skill for controlling apps, windows, dialogs, and websites through the peekaboo command-line tool. It first uses macOS accessibility information and can fall back to screenshots, coordinates, JavaScript, or visual recognition when needed.

Use it to inspect and operate Safari or native macOS apps, type text, click controls, press keyboard shortcuts, handle dialogs, and run multi-step workflows.

It helps automate interfaces that do not expose every control reliably through one method, while handling changing screens and recovery from failed interactions.

peekaboo — Skill for Claude Code and Codex by buildoak

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 buildoak/fieldwork-skills --skill peekaboo

Clone the repo

git clone --depth 1 https://github.com/buildoak/fieldwork-skills

Made for: Claude Code, Codex.

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/skills/buildoak/fieldwork-skills/peekaboo/github.svg)](https://agentmods.dev/skills/buildoak/fieldwork-skills/peekaboo)

Your own site

<a href="https://agentmods.dev/skills/buildoak/fieldwork-skills/peekaboo"><img src="https://agentmods.dev/badge/skills/buildoak/fieldwork-skills/peekaboo/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/skills/buildoak/fieldwork-skills/peekaboo"><img src="https://agentmods.dev/badge/skills/buildoak/fieldwork-skills/peekaboo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,956 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.

Model	Per session	Once invoked
Fable 5.1	$0.00054	$0.02956
Opus 5.5	$0.00022	$0.01182
Sonnet 5.5	$0.00011	$0.00591
Haiku 4.5	$0.00005	$0.00296

Measured 1mo ago against content hash 595febc460ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

peekaboo 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/health-check.sh, scripts/peekaboo-safe.sh), 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.

skills/peekaboo/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Peekaboo

Native macOS GUI automation via peekaboo, using an AX-first hybrid approach that prioritizes accessibility-tree interaction when reliable and switches to screenshot, coordinate, JavaScript, or vision-based fallbacks when AX coverage breaks down in real apps.

Terminology used in this file:

AX (Accessibility tree): The macOS accessibility hierarchy used for deterministic element discovery and interaction (B1, T2, etc.).
peekaboo: The macOS automation CLI used for discovery (see, image), interaction (click, type, hotkey), and app/window/dialog control.
UI-TARS: Vision model server used when AX discovery fails or times out on complex UIs.
FSM: Finite State Machine controlling retries, transitions, and recovery paths.
Retina scale: Display pixel ratio (typically 2.0) used to map screenshot coordinates correctly on Retina displays.
snapshot ID: The snapshot_id returned by see; required for stable element resolution and invalidated by UI changes.

Setup

brew install jq
brew install --cask peekaboo
mkdir -p ./scripts
chmod +x ./scripts/peekaboo-safe.sh ./scripts/health-check.sh
./scripts/health-check.sh

Grant Accessibility and Screen Recording permissions for your terminal agent host (for example, Terminal, iTerm2, Claude Code).
Use ./scripts/peekaboo-safe.sh as the only invocation entrypoint for peekaboo commands.
For full setup details and troubleshooting, see references/installation-guide.md if present in your local skill copy.

Staying Updated

This skill ships with an UPDATES.md changelog and UPDATE-GUIDE.md for your AI agent.

After installing, tell your agent: "Check UPDATES.md in the peekaboo skill for any new features or changes."

When updating, tell your agent: "Read UPDATE-GUIDE.md and apply the latest changes from UPDATES.md."

Follow UPDATE-GUIDE.md so customized local files are diffed before any overwrite.

Quick Start

Run a 3-step baseline flow: health check, discover, interact.

Read the full file on GitHub · 231 lines

Files

What ships with it

24 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.

1mo ago First seen · 231 lines · 54 tokens per session scan A 595febc460ea

Subscribe to this mod's changes

peekaboo is a skill published in the GitHub repository buildoak/fieldwork-skills (15 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 2,956 once invoked, about $0.0002 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.

Browser automation Claude Code agent-skills ai-agents ai-tools automation browser-automation

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.

browser-use/browser-use · 57 tokens

x402

Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…

browser-use/browser-use · 175 tokens

remote-browser

Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.

browser-use/browser-use · 22 tokens

cloud

Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…

browser-use/browser-use · 177 tokens

opencli-autofix

Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.

jackwener/OpenCLI · 61 tokens

opencli-adapter-author

Build or improve an OpenCLI JS adapter using observed site behavior, existing adapters and browser API evidence. For ad-hoc browser interaction, see opencli-browser.

jackwener/OpenCLI · 38 tokens