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.
npx agentmods add commands/openclaw/peekaboo/verifygit clone --depth 1 https://github.com/openclaw/PeekabooWhat 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 | $0.00000 | $0.00583 |
| Opus 5 | $0.00000 | $0.00292 |
| Sonnet 5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
verify 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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
peekaboo verify
peekaboo verify polls fresh native window and accessibility state until every requested predicate is stable or the timeout expires. It is the deterministic replacement for sleep-based polling: the command never focuses, clicks, types, or treats an incomplete observation as success.
Results are ternary. satisfied exits 0, unsatisfied exits 1, and unknown exits 2. Evaluated results in JSON output include every predicate result and an unknown_reason field; it is null when the result is not unknown.
Tool failures that prevent evaluation also exit 2. These failures use the standard error envelope in JSON mode, without predicate results or an unknown_reason field.
Key options
| Flag | Description |
|---|---|
| Target flags | --app, --pid, --window-id, --window-title, and --window-index use the shared target grammar. |
--window-exists |
Require the resolved target window to exist. |
--window-bounds x,y,w,h[,tolerance] |
Require exact logical-point bounds, with an optional per-component tolerance (default 1). |
--on <id-or-role:label> |
Select an element by opaque ID (for example B7) or exact role and label (for example button:Reload). |
--exists |
Require the selected element to exist. |
--value-equals <value> |
Require its accessibility value to match exactly. |
--enabled / --selected |
Require the corresponding accessibility state. |
--timeout <duration> |
Polling timeout (default 5s, maximum 10s; bare values are milliseconds). |
--stable-samples <n> |
Consecutive identical satisfied samples required (default 2). |
--screenshot <path> |
Save one final exact-window PNG when capture is available. |
--json |
Emit structured status, predicate results, timing, and the unknown reason. |
Examples
peekaboo verify --app Safari --window-exists
peekaboo verify --app Safari --on button:Reload --exists --enabled --json
peekaboo verify --pid 1234 --window-bounds 40,80,1200,800,2 --timeout 10s
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.
- 2d ago First seen · 41 lines · 0 tokens per session scan A 2f7fbd90164d
verify is a command published in the GitHub repository openclaw/Peekaboo (5,098 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 583 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.
Other commands, from other repositories
upload
Archive, upload, and submit to external TestFlight (full loop with monitor).
release
Create a new Remarc release using the automated GitHub Actions workflow.
imark-review
Open a markdown document in Imark for review and wait for the reviewer's notes.
imark-notes
Read the Imark comments out of a markdown file.
archive
Create xcarchive for TestFlight.
build
Build debug and launch HomeClaw.