personal-computer

by Dennis Nasarov · ★ 0 · updated 12 days ago

PanesStatus lineReskinsGuardsCommandsPromptvalidates

0

Keeps personal data out of Claude: every tool output is scanned on your machine (OpenAI Privacy Filter and PII-Tracer), and output with personal data is processed by a private model you choose through anymodel, while Claude orchestrates.

install personal-computer

Install

/plugin marketplace add ph3on1x/agent-plugins-skills
/plugin install personal-computer@ph3on1x

Then run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.

View source on GitHub

What it hooks into

From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.

Events
session.startui.rendercommand.runtool.callanymodel.screenprompt.submitsession.appendprompt.attachmentprompt.mention
API calls
$.anymodel.agents$.clock.after$.command.register$.config.set$.env.get$.fs.exists$.fs.read$.fs.stat$.fs.write$.http.fetch$.process.run$.process.spawn$.session.id$.session.messages$.settings.read$.state.get$.state.set$.store.get$.store.set$.ui.ask$.ui.open$.ui.resolve$.ui.status$.ui.toast
Draws
SessionModePane
Can see
every tool callevery prompt
Reach
level 3 of 3 networkruns processeswrites fileschanges configreads filesreads env varsreads settingsreads the transcriptreads mod statepersists statedrawsother: $.anymodel.agents

Origin

How it got here
Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
Repository
github.com/ph3on1x/agent-plugins-skills
Path in repo
plugins/personal-computer
Source commit
63d5df0 the exact code the scan read
Author
Dennis Nasarov @ph3on1x
License
MIT
First published
Last pushed
First listed here

Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.

More from ph3on1x/agent-plugins-skills

anymodel

ph3on1x/agent-plugins-skills

Claude Code subagents on the models you choose: name as many agents as you like, each on a model from your own providers (LM Studio, Unsloth Studio, llama.cpp, vLLM, OpenRouter, any Anthropic-compatible API), and call them like Claude's own subagents while the main session stays on Claude.

★ 0ToastsCommandsPrompt

refine-prompt

ph3on1x/agent-plugins-skills

Interview-style prompt refiner that picks a framework, fills gaps via AskUserQuestion, assembles a structured XML prompt, confirms, then executes it. In Claude Code, adds a refine prompt button above the prompt box.

★ 0Bands