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/spacegit 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 | $0.00748 |
| Opus 5 | $0.00000 | $0.00374 |
| Sonnet 5 | $0.00000 | $0.00150 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
space 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
peekaboo space
space wraps Peekaboo’s SpaceManagementService (private macOS APIs) to list Spaces, switch among them, and move windows. It’s best-effort—Apple may change these APIs—but it gives agents a reliable hook into Mission Control style workflows.
Subcommands
| Name | Purpose | Key options |
|---|---|---|
list |
Enumerate Spaces (per display) and, optionally, every window assigned to them. | --detailed triggers a per-window crawl so you see which apps live on each Space. |
switch |
Jump to a Space by number. | --to <n> (1-based) plus required --foreground consent. The command validates against the current count. |
move-window |
Move an app window to another Space or the current one. | --window-id selects an exact window without an app; otherwise use --app or --pid with at most one of --window-title or --window-index. Add --to <n> or --to-current; --follow --foreground explicitly switches to the destination Space after moving. |
Implementation notes
list --detailedenumerates every running app, lists its windows viaapplications.listWindows, and maps them back to Spaces using CoreGraphics window IDs. That means it may take a second on multi-display setups but yields accurate assignments.switchandmove-windowboth callSpaceCommandEnvironment.service, which can be overridden in tests; production runs use the live actor that talks to SpaceManagementService.move-windowreusesWindowIdentificationOptions, so apps can be resolved via names orPID:1234, and you can specify a particular window by title or index.- Plain window placement stays in the background.
switchandmove-window --followrefuse before inventory lookup or mutation unless--foregroundis explicit, because both replace the user's visible Space. MCP callers use the equivalentforeground: trueconsent. - A followed move composes the native move and switch receipts. Confirmed no-change, confirmed change, partial, and indeterminate switch results retain their real dispatch counts and retry semantics instead of being rewritten as a synthetic success.
- JSON output from
listis a compact{spaces:[{id,type,is_active,display_id}]}structure; action subcommands return{action,success,...}payloads that match the arguments you passed (space number, window title, follow flag, etc.).
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 · 44 lines · 0 tokens per session scan A 16cb7898a4e9
space 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 748 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.