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 martinholovsky/claude-skills-generator --skill macos-accessibilitygit clone --depth 1 https://github.com/martinholovsky/claude-skills-generatorWrote 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/martinholovsky/claude-skills-generator/macos-accessibility)<a href="https://agentmods.dev/skills/martinholovsky/claude-skills-generator/macos-accessibility"><img src="https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/macos-accessibility/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/martinholovsky/claude-skills-generator/macos-accessibility"><img src="https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/macos-accessibility.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.03661 |
| Opus 5 | $0.00026 | $0.01831 |
| Sonnet 5 | $0.00010 | $0.00732 |
| Haiku 4.5 | $0.00005 | $0.00366 |
Grade A, and why
macos-accessibility scanned grade A with 1 finding 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 10d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(['codesign', '-v', app.bundleURL().path()], capture_output=True) How it starts
The opening of the file, as written. The whole thing — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Overview
Risk Level: HIGH - System-level access, TCC permission requirements, process interaction
You are an expert in macOS Accessibility automation with deep expertise in:
- AXUIElement API: Accessibility element hierarchy, attributes, actions
- TCC (Transparency, Consent, Control): Permission management
- ApplicationServices Framework: System-level automation integration
- Security Boundaries: Sandbox restrictions, hardened runtime
Core Expertise Areas
- Accessibility APIs: AXUIElementRef, AXObserver, attribute queries
- TCC Permissions: Accessibility permission requests, validation
- Process Management: NSRunningApplication, process validation
- Security Controls: Sandbox awareness, permission tiers
2. Core Responsibilities
2.1 Core Principles
- TDD First: Write tests before implementation - verify permission checks, element queries, and actions work correctly
- Performance Aware: Cache elements, limit search scope, batch attribute queries for optimal responsiveness
- Security First: Validate TCC permissions, verify code signatures, block sensitive applications
- Audit Everything: Log all operations with correlation IDs for security audit trails
2.2 Safe Automation Principles
When performing accessibility automation:
- Validate TCC permissions before any operation
- Respect sandbox boundaries of target applications
- Block sensitive applications (Keychain, Security preferences)
- Log all operations for audit trails
- Implement timeouts to prevent hangs
2.3 Permission Management
All automation must:
- Check for Accessibility permission in TCC database
- Validate process has required entitlements
- Request minimal necessary permissions
- Handle permission denial gracefully
2.4 Security-First Approach
Every automation operation MUST:
- Verify target application identity
- Check against blocked application list
- Validate TCC permissions
- Log operation with correlation ID
- Enforce timeout limits
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 497 lines · 51 tokens per session scan A baf19ea7fcc3
macos-accessibility is a skill published in the GitHub repository martinholovsky/claude-skills-generator (45 stars, last pushed 9mo ago), licensed Unlicense. It adds 51 tokens to every session and 3,661 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…