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 rayss868/pc-controller-mcp-server --skill skillgit clone --depth 1 https://github.com/rayss868/pc-controller-mcp-serverWrote 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/rayss868/pc-controller-mcp-server/skill)<a href="https://agentmods.dev/skills/rayss868/pc-controller-mcp-server/skill"><img src="https://agentmods.dev/badge/skills/rayss868/pc-controller-mcp-server/skill/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/rayss868/pc-controller-mcp-server/skill"><img src="https://agentmods.dev/badge/skills/rayss868/pc-controller-mcp-server/skill.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 | $0.00082 | $0.02938 |
| Opus 5.5 | $0.00033 | $0.01175 |
| Sonnet 5.5 | $0.00016 | $0.00588 |
| Haiku 4.5 | $0.00008 | $0.00294 |
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 2mo 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.
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") How it starts
The opening of the file, as written. The whole thing — 246 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 (41 tools). Commands run via cmd (default), with PowerShell / Git Bash / WSL available on request.
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:
- Is there a dedicated tool that solves this in one obvious call? → use the tool
- Otherwise → use
run_command(orrun_command_long/execute_code)
Streaming sessions (reuse ONE terminal, realtime)
For anything that needs state across commands — a dev server, watch/build loop, SSH,
a database CLI — do NOT spawn a new shell per command. Open ONE persistent terminal with
session_id and stream every later command through the same shell, realtime:
# STEP 1 — open the terminal (wait for the confirmation return)
pc-controller:terminal_open(session_id="dev", title="OpenAI", cwd="C:\\Users\\<username>\\Projects\\app")
# STEP 2 — stream commands into the open terminal
pc-controller:run_command(command="npm run dev", session_id="dev")
pc-controller:run_command(command="", session_id="dev", wait_ms=5000) # block & fetch new output
pc-controller:interact_with_process(session_id="dev", input="", wait_ms=2000)
pc-controller:list_sessions()
pc-controller:terminal_stop(session_id="dev")
Rules:
- STEP 1: open the terminal with
terminal_openand wait for its confirmation before sending anything. STEP 2: everyrun_commandcall with the SAME id streams into that open terminal — same shell, same cwd, same variables. The shell is NOT reopened per command. run_commandwith asession_idthat is NOT open returns an error: open it first.- Different
session_id= a separate terminal, streamed side by side. Open as many as needed. shell/cwd/titleare fixed when the terminal opens; afterwards navigate withcd.- The terminal opens as a visible console window. Use
titleinterminal_opento customize its window title; if omitted, it defaults toPC Controller - <session_id>. - Close a session with
terminal_stop(kills the whole process tree). - Idle auto-close: a session dies automatically after 10 minutes without ANY activity (no output AND no input). Any streamed output or sent input resets the timer.
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.
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.
- 2mo ago Changed · +38 lines edae4bf4024c
- 2mo ago First seen · 208 lines · 82 tokens per session scan B ba95e0a9b2f9
pc-controller is a skill published in the GitHub repository rayss868/pc-controller-mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 2,938 once invoked, about $0.0003 per session on Opus 5.5. 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.
pc-controller compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pc-controllerrayss868/pc-controller-mcp-server | Skill | 1 | 2mo ago | MIT | B | 82 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 101k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 81k | 5d ago | MIT | A | 200 | Claude Code, Codex |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | yesterday | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |