pc-controller

A tool for controlling a Windows 10 or 11 computer through commands and connected controls. It can work with files, programs, processes, screenshots, the clipboard, terminals, and system information.

In plain words
What is it for?
Use it to run PowerShell, Git Bash, or WSL commands; read and edit files; capture the screen; manage processes and terminals; inspect system information; handle archives; or fetch URLs.
Why use it?
It lets an agent carry out computer-management tasks remotely through one set of controls. This avoids switching between separate tools for routine Windows operations.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/rayss868/pc-controller-mcp-server/skill
Any agent
npx skills add rayss868/pc-controller-mcp-server --skill skill
Clone the repo
git clone --depth 1 https://github.com/rayss868/pc-controller-mcp-server

Made for: Claude Code, Codex.

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,274 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00082 $0.02274
Opus 5 $0.00041 $0.01137
Sonnet 5 $0.00016 $0.00455
Haiku 4.5 $0.00008 $0.00227

Measured yesterday against content hash ba95e0a9b2f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

pc-controller scanned grade B 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 yesterday.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

pc-controller:run_command(command="sudo apt update", shell="wsl")
skill/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PC Controller

Control this Windows PC using the pc-controller MCP server (38 tools). All tools run via PowerShell on Windows 10/11.

Command-First Principle

run_command is the universal center. Anything PowerShell/Git Bash/WSL can do, it can do — there is no task that requires a dedicated tool. Dedicated tools are conveniences: use one only when it is clearly simpler than writing the equivalent command.

Decision rule:

  1. Is there a dedicated tool that solves this in one obvious call? → use the tool
  2. Otherwise → use run_command (or run_command_long / execute_code)

Use tools when simple

Task Use
Read/edit small text file file_read / file_edit
View image inline preview_file
See the screen screen_capture
Copy/paste clipboard text clipboard_get / clipboard_set
Kill a known process process_kill
Zip/unzip archive zip_create / zip_extract

Fall back to run_command for everything else

Anything not covered above — document parsing, registry, services, network diagnostics, environment variables, scheduled tasks, WMI queries, multimedia metadata, etc. Examples:

# Read DOCX text (Word COM)
$w = New-Object -ComObject Word.Application; $d = $w.Documents.Open("C:\path\file.docx"); $d.Content.Text; $d.Close(); $w.Quit()

# Read XLSX data (Excel COM)
$x = New-Object -ComObject Excel.Application; $wb = $x.Workbooks.Open("C:\path\file.xlsx"); $wb.Sheets.Item(1).UsedRange.Value2

# Read PDF text (requires pdftotext: scoop install poppler / choco install poppler)
pdftotext C:\path\file.pdf -

# Read PDF via Python (no extra CLI needed)
python -c "import pypdf,sys; print('\n'.join(p.extract_text() for p in pypdf.PdfReader(sys.argv[1]).pages))" C:\path\file.pdf

# Environment variables, registry, services
Get-ChildItem Env:  |  Get-ItemProperty "HKLM:\SOFTWARE\..."  |  Get-Service

When in doubt, just run the command.

Tool Reference

Shell Execution

Read the full file on GitHub · 208 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. yesterday First seen · 208 lines · 82 tokens per session scan B ba95e0a9b2f9

Subscribe to this mod's changes

pc-controller is a skill published in the GitHub repository rayss868/pc-controller-mcp-server (0 stars, last pushed 11d ago), licensed MIT. It adds 82 tokens to every session and 2,274 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens