agent

A command-line interface for Peekaboo’s computer-control agent, which carries out tasks described in ordinary language. It can run, resume, inspect, and chat through agent sessions.

In plain words
What is it for?
Use it to run natural-language tasks, resume previous agent sessions, start interactive chats, preview a task without running it, and limit the number of steps.
Why use it?
It gives you one way to start and continue automated computer tasks without manually coordinating each interaction.

Command

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 commands/openclaw/peekaboo/agent
Clone the repo
git clone --depth 1 https://github.com/openclaw/Peekaboo
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,299 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 $0.00000 $0.03299
Opus 5 $0.00000 $0.01649
Sonnet 5 $0.00000 $0.00660
Haiku 4.5 $0.00000 $0.00330

Measured 2d ago against content hash f65f53e264f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent 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 2d 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.

docs/commands/agent.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

peekaboo agent

agent hands a natural-language task to PeekabooAgentService, which in turn orchestrates the full toolset (see, click, type, menu, etc.). The command handles session caching, terminal capability detection, progress spinners, and audio capture so you can run the exact same agent loop the macOS app uses.

Subcommands and options

Command or flag Description
run [task] Run a task. run is the default, so peekaboo agent "task" remains valid.
resume [session-id] Resume the most recent session, or the exact full session ID, in chat mode.
sessions Print cached sessions with full IDs, tasks, lifecycle status, and stored policy maximum; accepts only the global --json output switch.
chat [initial-prompt] Start the interactive chat loop.
--dry-run Emit a deterministic preview of a required text task without calling a model, invoking tools, transcribing audio, or creating a session. Human output names the requested foreground choice and effective UI authority. JSON also includes uiAuthority.requestedForeground, uiAuthority.effectivePolicy, and uiAuthority.backgroundOnly.
--max-steps <n> Cap model turns to 1...100 (default: 100). One turn may contain multiple tool calls.
`--model gpt-5.6 gpt-5-mini
--no-cache Run ephemerally without saving a resumable session. Cannot be combined with resume/list flags.
--allow-foreground Human opt-in for this invocation to use foreground/global UI routes. New sessions persist it as an immutable maximum; each later resume must opt in again. It never exposes the Shell tool.
--quiet / --simple / --no-color / --debug-terminal Control output mode; the command auto-detects terminal capabilities when you don’t override it.
--audio / --audio-file <path> Use microphone input or pipe audio from disk.

Read the full file on GitHub · 174 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. 2d ago First seen · 174 lines · 0 tokens per session scan A f65f53e264f8

Subscribe to this mod's changes

agent is a command published in the GitHub repository openclaw/Peekaboo (5,098 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,299 tokens. 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.