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/permissionsgit clone --depth 1 https://github.com/openclaw/PeekabooWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/openclaw/peekaboo/permissions)<a href="https://agentmods.dev/commands/openclaw/peekaboo/permissions"><img src="https://agentmods.dev/badge/commands/openclaw/peekaboo/permissions.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01106 |
| Opus 5 | $0.00000 | $0.00553 |
| Sonnet 5 | $0.00000 | $0.00221 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
permissions 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 4d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
peekaboo permissions
peekaboo permissions centralizes entitlement checks. The default status subcommand reports the runtime view of Screen Recording, Accessibility, and Event Synthesizing. grant prints the same table plus human-readable steps so you can fix issues without hunting through docs.
Status is one snapshot from the execution host selected by normal runtime routing. A Bridge-backed CLI or MCP session therefore reports the Bridge host's three grants with one request; it never mixes remote Screen Recording or Accessibility with caller-local Event Synthesizing state. Screen Recording and Accessibility are required. Event Synthesizing remains optional globally and is reported with the actions it limits: background keyboard input and foreground synthetic pointer input.
Peekaboo's application, Dock, and UI operations use native macOS APIs. It does not probe, request, or require Automation (AppleScript) permission. The Bridge protocol still decodes the legacy field so mixed-version clients receive a structured compatibility result instead of failing the whole handshake. If an older Bridge host reports an AppleScript denial, update the CLI and Bridge host instead of granting Automation access; current hosts perform these operations natively.
Subcommands
| Name | Purpose |
|---|---|
status (default) |
Fetches the current permission set and prints each entry (granted, denied, etc.). Honors --json so agents can block proactively. Add --all-sources to compare Bridge and local CLI permissions side by side. |
grant |
Reuses the same snapshot but focuses on remediation: when in text mode it prints the exact System Settings pane/location for each missing entitlement. |
request <kind> |
Request accessibility, screen-recording, or event-synthesizing. Screen Recording and Accessibility target the local process; Event Synthesizing follows runtime routing unless --no-remote is used. |
Implementation notes
- All subcommands conform to
RuntimeOptionsConfigurable, so they inherit global--json/--verboseflags even when invoked from compound commands likepeekaboo learn. - The command executes entirely on the main actor, avoiding extra prompts or sandbox warnings—the same code path runs at CLI startup to warn if entitlements are missing.
- JSON mode uses
outputSuccessCodable, which means status results include apermissionsarray with{name, isRequired, isGranted, grantInstructions}entries that can be diffed over time. --all-sources --jsonreturns{selectedSource, sources}so callers can distinguish Bridge TCC grants from local CLI grants.- The MCP
permissionstool returns an error when either required permission is missing, while retaining all three permission fields and the action-specific Event Synthesizing limitations in response metadata.
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.
- 4d ago First seen · 77 lines · 0 tokens per session scan A 9d75fe5d5fd4
permissions is a command published in the GitHub repository openclaw/Peekaboo (5,098 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,106 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.