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 skills add johnkozaris/jko-claude-plugins --skill validate-macos-appgit clone --depth 1 https://github.com/johnkozaris/jko-claude-pluginsWrote 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/johnkozaris/jko-claude-plugins/validate-macos-app)<a href="https://agentmods.dev/skills/johnkozaris/jko-claude-plugins/validate-macos-app"><img src="https://agentmods.dev/badge/skills/johnkozaris/jko-claude-plugins/validate-macos-app.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 5.1 | $0.00021 | $0.00689 |
| Opus 5 | $0.00010 | $0.00345 |
| Sonnet 5 | $0.00004 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
validate-macos-app 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 8d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate macOS App
Invoke peekaboo and validate $ARGUMENTS.
Parse the first argument as the required bundle ID. Treat the remaining text as
optional comma-separated view labels so labels may contain spaces. Parse this in
the agent; do not execute $1/shift in a fresh shell.
Preflight and ownership
Check peekaboo, jq, selected-runtime permissions, and live help. Use
the primary peekaboo skill's setup diagnosis for missing prerequisites.
Before launch, query peekaboo list apps --json for the bundle ID and record
whether it is already running. Launch only when absent. Cleanup may quit the app
only when this command launched it; preserve a pre-existing process and report
that choice.
Use an artifact directory outside version control. Add the directory to
.gitignore when it lives under the repository. Track every task-created path
for cleanup.
Observe and choose states
Predict JSON response size before each command. Persist every see,
inspect-ui, browser snapshot, capture result, or other likely-large response
to a named file and query only the fields needed for targeting and assertions.
If view labels were supplied, validate those. Otherwise discover likely top-level navigation controls from roles and hierarchy. Do not include destructive or irreversible controls such as delete, send, publish, purchase, sign-out, or account mutation unless the user named them.
Before each action, define the expected product state: selected tab, heading, visible control, value, window, persisted output, or another specific postcondition. A changed tree or screenshot hash is supporting evidence, not the postcondition.
Resolve exactly one actionable target from the latest snapshot. On zero or multiple matches, refine from hierarchy/identifier or stop rather than clicking an arbitrary result. Treat IDs as opaque and capture fresh state after every mutation.
Visual evidence
Treat every screenshot as large. Capture raw and annotated images only when each answers a distinct question. Give a visual reader the minimum related paths and request a compact report. As soon as it returns, terminate it with the host's kill/stop/remove control and verify through worker listing that it is gone. A blocking or synchronous result does not prove teardown.
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.
- 8d ago First seen · 78 lines · 21 tokens per session scan A 8154ee20dc12
validate-macos-app is a skill published in the GitHub repository johnkozaris/jko-claude-plugins (11 stars, last pushed 11d ago), licensed MIT. It adds 21 tokens to every session and 689 once invoked, about $0.0001 per session on Opus 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
dotnet-backend-expert
This skill should be used when the user is writing, reviewing, debugging, or architecting pure .NET backend code for Kestrel-hosted services. It provides expert critique for REST endpoints, SignalR hubs, TypeScript/React client integration shape, pragmatic Rust interop, application services, AppHost-aware project…
esp32-expert
This skill should be used when the user is writing, reviewing, debugging, or architecting C++ firmware for ESP32 and variants (ESP32-S2, S3, C3, C6, H2, P4) using ESP-IDF or PlatformIO. Provides expert critique covering FreeRTOS task design, memory management (IRAM/DRAM/PSRAM), peripheral drivers (I2C/SPI/UART/GPIO)…
python-backend-expert
This skill should be used when the user is writing, reviewing, debugging, or architecting Python backend code using Litestar or FastAPI with SQLAlchemy or Advanced Alchemy. Provides expert critique covering SOLID principles, hexagonal architecture, repository/service patterns, dependency injection, async correctness…
rust-expert
This skill should be used when the user is writing, reviewing, debugging, or architecting Rust code. Detects edition and toolchain from the project. Provides expert critique covering ownership, error handling, unsafe review, async correctness, trait design, type system patterns, performance, SOLID principles, and…
swiftui-expert
This skill should be used when the user is building, reviewing, or debugging SwiftUI views and apps. Detects iOS and Swift version from the project. Covers creating views, state management with @Observable, NavigationStack routing, animations, accessibility, performance optimization, Liquid Glass adoption, design…
dead-code-expert
This skill should be used when the user wants to find, audit, or remove dead code, unused imports, unused functions, unused variables, duplicate implementations, or simplify a codebase. Works across all programming languages. Relevant when the user says "find dead code", "remove dead code", "remove unused imports"…