ai-skills

A Claude Code mod in BenjaminG/ai-skills

Benjamin's collection of Claude Code skills: daily workflow, code quality, dev tools, and specialist agents.

ai-skills reaches L3 (network) by its classified calls and passed claude plugin validate with warnings on Claude Code 2.1.302.

Events hooked: 9
API methods referenced: 27
Access from classified calls: L3, network: MCP servers, runs processes, writes files, drives Claude, writes the prompt box, reads files, persists state, draws
Unclassified calls: 1 ($.process.spawn), full access unknown
Static scan, not a runtime test

To install it, open the repository and follow the author’s setup instructions. Mods need Claude Code 2.1.287 or later.

Access

L3 Uses the networkother: $.process.spawn, MCP servers, runs processes, writes files, drives Claude, writes the prompt box, reads files, persists state, draws

Validation

Passed with warnings on Claude Code 2.1.302

View the source on GitHub Back to the list

What the scan recorded

Observed events: every skill, Skill calls, every prompt
Hooks: session.start, command.run {command=prs}, ui.close {id=prs}, ui.render {component=Pane, requestId=prs}, command.run {command=wt}, ui.close {id=wt}, ui.render {component=Pane, requestId=wt}, skill.prompt, command.run {command=xray}, ui.close {id=xray}, ui.render {component=Pane, requestId=xray}, tool.call {tool=Skill}, prompt.submit, turn.complete, prompt.suggest {origin has {kind=suggestion}, command.run {command=shepherd}, turn.complete {agentId=/"^a[0-9a-f]+$"/}, command.run {command=slack-follow}, command.run {command=slack-unfollow}
API calls: $.agent.list, $.agent.spawn, $.clock.after, $.clock.every, $.clock.now, $.command.register, $.fs.exists, $.fs.list, $.fs.read, $.fs.stat, $.fs.write, $.mcp.call, $.process.run, $.process.spawn, $.prompt.fill, $.prompt.submit, $.prompt.suggest, $.store.get, $.store.set, $.tool.call, $.ui.close, $.ui.invalidate, $.ui.log, $.ui.open, $.ui.resolve, $.ui.status, $.ui.toast
Validation on 2.1.302: Passed with warnings
Scanned revision: e60de0495d18

These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. How the scan works.

Badge for your README

Authors can show the latest scan result in their README. Each badge links to this page.

[![reach](https://raw.githubusercontent.com/karanb192/awesome-claude-code-mods/main/badges/BenjaminG--ai-skills--ai-skills-reach.svg)](https://mods.aidojo.si/mods/BenjaminG--ai-skills--ai-skills/)
[![validates](https://raw.githubusercontent.com/karanb192/awesome-claude-code-mods/main/badges/BenjaminG--ai-skills--ai-skills-validates.svg)](https://mods.aidojo.si/mods/BenjaminG--ai-skills--ai-skills/)