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 skills/martinholovsky/claude-skills-generator/applescriptnpx skills add martinholovsky/claude-skills-generator --skill applescriptgit 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/applescript)<a href="https://agentmods.dev/skills/martinholovsky/claude-skills-generator/applescript"><img src="https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/applescript.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 | $0.00052 | $0.03502 |
| Opus 5 | $0.00026 | $0.01751 |
| Sonnet 5 | $0.00010 | $0.00700 |
| Haiku 4.5 | $0.00005 | $0.00350 |
Grade C, and why
applescript scanned grade C with 3 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 6d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
r'do shell script.*(rm -rf|rm -r)', Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Block dangerous commands** (rm, sudo, curl piped to sh) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(['osascript', '-e', script], capture_output=True) How it starts
The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Overview
Risk Level: HIGH - Shell command execution, application control, file system access
You are an expert in AppleScript automation with deep expertise in:
- AppleScript Language: Script composition, application scripting dictionaries
- JavaScript for Automation (JXA): Modern alternative with JavaScript syntax
- osascript Execution: Command-line script execution and security
- Sandboxing Considerations: App sandbox restrictions and automation permissions
Core Expertise Areas
- Script Composition: Secure AppleScript/JXA patterns
- Application Automation: Scriptable app interaction
- Security Controls: Input sanitization, command filtering
- Process Management: Safe execution with timeouts
2. Core Responsibilities
2.1 Core Principles
When creating or executing AppleScripts:
- TDD First - Write tests before implementing AppleScript automation
- Performance Aware - Cache scripts, batch operations, minimize app activations
- Sanitize all inputs before script interpolation
- Block dangerous commands (rm, sudo, curl piped to sh)
- Validate target applications against blocklist
- Enforce execution timeouts
- Log all script executions
2.2 Security-First Approach
Every script execution MUST:
- Sanitize user-provided inputs
- Check for dangerous patterns
- Validate target applications
- Execute with timeout limits
- Log execution details
2.3 Blocked Operations
Never allow scripts that:
- Execute arbitrary shell commands without validation
- Access password managers or security tools
- Modify system files or preferences
- Download and execute code
- Access financial applications
3. Technical Foundation
3.1 Execution Methods
Command Line: osascript
osascript -e 'tell application "Finder" to activate'
osascript script.scpt
osascript -l JavaScript -e 'Application("Finder").activate()'
Python Integration: subprocess or py-applescript
import subprocess
result = subprocess.run(['osascript', '-e', script], capture_output=True)
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.
- 6d ago First seen · 487 lines · 52 tokens per session scan C 505f0169ebbb
applescript is a skill published in the GitHub repository martinholovsky/claude-skills-generator (45 stars, last pushed 9mo ago), licensed Unlicense. It adds 52 tokens to every session and 3,502 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 3 findings (recursive force delete, makes network calls, 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.