tools

A command for listing and inspecting the tools available through Peekaboo, an interface-automation system. It can show tool names, descriptions, schemas, and machine-readable JSON output.

In plain words
What is it for?
Use it to list Peekaboo tools, inspect one tool's input format, preserve registration order, or obtain tool data for scripts.
Why use it?
It helps you discover which automation actions are available before trying to use them.

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/tools
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 727 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 $0.00727
Opus 5 $0.00000 $0.00364
Sonnet 5 $0.00000 $0.00145
Haiku 4.5 $0.00000 $0.00073

Measured 2d ago against content hash 3944fb7aad91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tools 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/tools.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

peekaboo tools

peekaboo tools prints the background-only MCP tool catalog that peekaboo mcp exposes (Image, See, Click, Press, Action, Window, Browser, Inspect UI, etc.). peekaboo tools describe <name> prints one tool's policy-aware JSON input schema for token-cheap, on-demand discovery. Tools with no background-safe form, such as move and drag, are omitted. Mixed-capability tools retain their background-safe actions and describe which foreground shapes require a human-authorized foreground Agent or standalone CLI route. The public Agent catalog is a separate Shell-free surface; run peekaboo learn for that exact guide. The CLI keeps browser as a dedicated wrapper and exposes AX-only inspection through peekaboo see --tree --no-screenshot; run peekaboo --help for the full CLI command list.

Key options

Flag Description
--no-sort Preserve registration order instead of alphabetizing every tool.
--verbose Include each tool's description alongside its name.
--json Emit {tools:[…], count:n} for machine parsing.

Subcommands

Name Purpose
describe <tool-name> Print the tool name, abstract, and pretty JSON input schema. With --json, emit {name, description, input_schema}. Unknown names fail and list every valid name.

Implementation notes

  • The command and MCP server both use MCPToolCatalog, so tool additions only need to be registered once.
  • Tool schemas receive the same execution policy as the catalog. Background app/window descriptions omit focus and switch actions, while foreground-capable Agent schemas expose them under explicit human authority.
  • Background clipboard discovery exposes only get and save. set, clear, and restore persistently change the user's shared clipboard state and require a foreground-authorized workflow; prefer exact targeted transactional paste when possible.
  • Allow/deny filtering happens before formatting (ToolFiltering.apply), so the output matches MCP server behavior.
  • Input-strategy availability filtering also runs before formatting, so action-only tools are hidden when the current policy cannot support them.
  • The command runs locally by default because it only reports the static native catalog; use per-tool wrappers or an attached MCP client to execute tools.
  • Because the command implements RuntimeOptionsConfigurable, it respects global --json/--verbose flags even when invoked from other commands (e.g., peekaboo learn can embed the summaries verbatim).

Read the full file on GitHub · 48 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 · 48 lines · 0 tokens per session scan A 3944fb7aad91

Subscribe to this mod's changes

tools 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 727 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.