Peekaboo is a macOS command-line tool and menu-bar app that captures screens, inspects accessibility information, and controls native user interfaces. AI agents and MCP clients use it to observe applications and carry out interactions on a Mac.
Borrowing it
Nothing to install: this file belongs to openclaw/Peekaboo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/openclaw/Peekaboo/main/.agents/skills/release-peekaboo/SKILL.mdgit 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/skills/openclaw/peekaboo/release-peekaboo)<a href="https://agentmods.dev/skills/openclaw/peekaboo/release-peekaboo"><img src="https://agentmods.dev/badge/skills/openclaw/peekaboo/release-peekaboo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/openclaw/peekaboo/release-peekaboo"><img src="https://agentmods.dev/badge/skills/openclaw/peekaboo/release-peekaboo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 64 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 5.1 | $0.00023 | $0.00623 |
| Opus 5.5 | $0.00009 | $0.00249 |
| Sonnet 5.5 | $0.00005 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
release-peekaboo 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 14d 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.
What it actually says
Peekaboo Release
Read docs/RELEASING.md first; it is the source of
truth. Follow repo AGENTS.md. Only .github/workflows/release.yml publishes
openclaw/Peekaboo and @steipete/peekaboo. Never release or publish without an
explicit release command; a rehearsal does not authorize publication.
- Prepare a PR with consistent version surfaces and dated root/CLI changelog
sections, validated by the existing release preflight. Hosted Actions extracts
notes from
CHANGELOG.md; no separate notes file or local publisher is used. Merge the preparation PR and wait for green push CI on that exact commit. - Rehearse from main with
gh workflow run release.yml --ref main -f version=X.Y.Z -F dry_run=true. Review the frozen source and artifacts, approve thereleaseenvironment, and verify the run succeeds without publication. - With explicit publication authorization, create and push an annotated
SSH-signed
vX.Y.Ztag on the same verified commit, using the canonical release SSH key accepted by.github/release-allowed-signers. Resolve that key through the private credential guidance if needed; never copy private key material into the repo. Approve the publication run'sreleaseenvironment gate. Tag pushes also trigger other workflows; the release CI gate fails while checks are still running. Wait for them to succeed, then rerun failed release jobs as needed. Never replace a published tag or rebuild an existing version. - Verify GitHub Release assets and
checksums.txt, and compare the published notes to the root changelog. Check npm's exact version, dist-tag, tarball, integrity and publish time; compare the downloaded registry tarball's SHA-512 integrity with the exact tarball from the hosted run. Run published CLI proof withnpm execfrom/tmpso the checkout cannot shadow the package. - Verify the Homebrew tap formula's version, URLs and checksums. Review and merge
the Actions-created appcast closeout PR, then verify the feed on main and the
post-release
Unreleasedsection. Report the release/run/closeout links and any incomplete handoff. Retry hosted handoffs only after checking what is already published; do not overwrite an existing version.
Signing/notarization credentials stay in the hosted release environment; npm
uses OIDC. Local terminal/fleet notarization helpers are qualification tools and
are not an alternate publication path.
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.
- 14d ago Changed · -156 lines · -5 tokens per session scan B → A f4f23108d9ff
- 24d ago Changed · +1 lines a2a555d5c5aa
- 25d ago Changed · +5 lines 8de474926872
- 27d ago Changed · +33 lines 0b24e7272cdb
- 1mo ago Changed f7eadec0f7a2
- 2mo ago First seen · 161 lines · 28 tokens per session scan B aee762ecf54d
release-peekaboo is a skill published in the GitHub repository openclaw/Peekaboo (5,403 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 623 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
release
Prepare, verify, and publish Sutando engine releases. Use when asked to prepare a release proposal, determine a version bump, audit release documentation, validate release gates, create a release PR, tag a confirmed release, or publish GitHub release notes. Preparation is safe and non-publishing; tagging and…
starcat-update-changelog
Update Starcat changelog documents in supports/starcat-pro/ by reading ALL git commits from the main Starcat project and generating categorized release notes in both English and Chinese. Use this skill whenever the user wants to update changelog, release notes, update records, or sync the changelog with recent…
publish-plugins
(project) Use when editing any file under skills/ or plugins/ to bump the plugin version and check the manifests.
release
Build, sign, notarize, and publish a new DroidProxy release. Use when the user wants to cut a release, merge a PR and ship it, or asks to build/notarize/publish. Covers the full pipeline: PR merge, version bump, swift build, code signing, Apple notarization, Sparkle appcast update, and GitHub release creation.
starcat-release-readiness
A release-readiness workflow for preparing and auditing a macOS app for the Mac App Store and direct distribution. It covers checks across branches, database changes, tests, builds, signing, notarisation, release notes, and human approval.
pr
Use when the user explicitly asks to push the current branch and open a PR, rewrite an open PR's body from its commits, or wait for CI and merge it.