peekaboo

A macOS tool for capturing screens, inspecting app windows and accessibility information, and controlling keyboard or mouse input.

In plain words
What is it for?
Use it to inspect user interfaces, take screenshots, examine accessibility trees, interact with apps, or automate Mac workflows.
Why use it?
It lets an agent observe and operate native Mac applications when text-only interaction is not enough.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/steipete/agent-scripts/peekaboo
Any agent
npx skills add steipete/agent-scripts --skill peekaboo
Clone the repo
git clone --depth 1 https://github.com/steipete/agent-scripts

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.01842
Opus 5 $0.00013 $0.00921
Sonnet 5 $0.00005 $0.00368
Haiku 4.5 $0.00003 $0.00184

Measured 3d ago against content hash bed6b305f5ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

skills/peekaboo/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Peekaboo

Use Peekaboo for native macOS capture, UI inspection, and automation. Prefer its native app, window, Accessibility, and input commands over AppleScript or osascript whenever Peekaboo exposes the operation.

Binary

  • Prefer ~/bin/peekaboo when present; it is Peter's signed local release copy.
  • Otherwise use peekaboo from PATH.
  • Check the selected binary before relying on syntax or installed state.
PB="${PEEKABOO_BIN:-$HOME/bin/peekaboo}"
[ -x "$PB" ] || PB="$(command -v peekaboo)"
"$PB" --version

Runtime host and permissions

  • Launch Peekaboo.app without taking focus when a GUI Bridge host is needed: open -gj -a Peekaboo.
  • The app owns its TCC grants and serves ~/Library/Application Support/Peekaboo/bridge.sock. The reusable daemon has separate permissions and serves daemon.sock; daemon start is not an app launch.
  • Ordinary runtime selection prefers a healthy reusable daemon, then the GUI host, before starting a daemon. Implicit screen-capture observation, AX-tree inspection, browser, and snapshot-state commands instead prefer and may auto-start the current CLI build's exact build-scoped daemon before the GUI host. Use bridge status --verbose --json to inspect candidates, but remember that operation requirements can change their order. When app-held TCC is required, pass --bridge-socket "$HOME/Library/Application Support/Peekaboo/bridge.sock" and verify hostKind: gui instead of assuming the app was selected.
  • Check permissions status --all-sources --json. Grant Screen Recording, Accessibility, and Event Synthesizing to the process reported as the selected source, not merely to the invoking terminal.
  • Prefer Bridge capture from SSH, LaunchAgent, Codex, and other background sessions. --no-remote --capture-engine cg is a local-debug override and can return wallpaper-only pixels outside the active Aqua session.
  • Never run an unsigned or ad-hoc build against saved TCC or Keychain state.

Read the full file on GitHub · 165 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.

  1. 3d ago First seen · 165 lines · 26 tokens per session scan A bed6b305f5ea

Subscribe to this mod's changes

peekaboo is a skill published in the GitHub repository steipete/agent-scripts (6,590 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,842 once invoked, about $0.0001 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens