Borrowing it
Nothing to install: this file belongs to chan4lk/claude-multi-channel-discord. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chan4lk/claude-multi-channel-discord/main/.claude/skills/run-windows/SKILL.mdgit clone --depth 1 https://github.com/chan4lk/claude-multi-channel-discordWrote 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/chan4lk/claude-multi-channel-discord/run-windows)<a href="https://agentmods.dev/skills/chan4lk/claude-multi-channel-discord/run-windows"><img src="https://agentmods.dev/badge/skills/chan4lk/claude-multi-channel-discord/run-windows/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/chan4lk/claude-multi-channel-discord/run-windows"><img src="https://agentmods.dev/badge/skills/chan4lk/claude-multi-channel-discord/run-windows.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 | $0.00077 | $0.01914 |
| Opus 5.5 | $0.00031 | $0.00766 |
| Sonnet 5.5 | $0.00015 | $0.00383 |
| Haiku 4.5 | $0.00008 | $0.00191 |
Grade A, and why
run-windows scanned grade A with 0 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 26d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run MCD on native Windows
On win32, MCD uses the headless backend: each channel runs as
claude -p --input-format stream-json --output-format stream-json over
pipes instead of in a tmux pane (src/claude-process.ts,
src/claude-bin.ts). No WSL, tmux or Git Bash is needed. Background
reading: docs/setup.md → "Windows".
All commands below run from the repo root in PowerShell. Windows PowerShell 5.1 is fine.
Never kill processes by name (
taskkill /im claude.exe,Stop-Process -Name claude, or a filter onstream-json). The Claude desktop app runs its ownclaude.exesessions, and this conversation may be one of them. MCD's children are theclaude.exeprocesses whose command line containsmcd-<slug>-…\mcp-config.json. To stop MCD, use the scripts below.If this session is itself running inside MCD (a project channel), don't stop or restart the bot. That ends your own session; see CLAUDE.md.
1. Check what's already done
Run these and skip the steps that are already satisfied:
$env:Path = [Environment]::GetEnvironmentVariable('Path','Machine') + ';' + [Environment]::GetEnvironmentVariable('Path','User')
bun --version; git --version
Test-Path "$HOME\.claude\channels\discord-multi\.env" # setup done?
Get-ScheduledTask multi-channel-discord -ErrorAction SilentlyContinue | Select TaskName, State
Check that the claude CLI is logged in. The headless backend uses
MCD_CLAUDE_BIN, then claude.exe on PATH, then the Claude desktop app's
bundled CLI. The app is MSIX-packaged, so outside the app that CLI lives
under %LOCALAPPDATA%\Packages\Claude_*\LocalCache\Roaming\Claude\claude-code\<ver>\<hash>\claude.exe.
bun -e "import('./src/claude-bin.ts').then(m => console.log(m.resolveClaudeBin()))"
& (bun -e "import('./src/claude-bin.ts').then(m => console.log(m.resolveClaudeBin()))") auth status
2. First-time setup
- Tools:
winget install --id Oven-sh.Bun -e --scope userandwinget install --id Git.Git -e. The Git installer asks for admin (UAC); the user approves it. Then runbun install --no-summary. - Claude login:
loggedIn: falseabove means the user must sign in. Open a terminal tab and run the resolvedclaude.exewithauth login. The user finishes it in the browser. Never handle their credentials yourself. - Discord bot: the user does this in the Developer Portal. Create an
application. On the Bot tab, enable Message Content Intent, then use
Reset Token. Invite it with scope
botand View Channels, Send Messages, Send Messages in Threads, Read Message History, Add Reactions and Manage Channels. With Developer Mode on in Discord, copy their user ID and the master channel ID. - State dir: start the setup in a terminal tab so the user types the values there. Never ask for the bot token in chat.
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.
- 26d ago First seen · 141 lines · 77 tokens per session scan A 3159f3af2ce3
run-windows is a skill published in the GitHub repository chan4lk/claude-multi-channel-discord (3 stars, last pushed 24d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,914 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.
run-windows compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| run-windowschan4lk/claude-multi-channel-discord | Skill | 3 | 24d ago | Apache-2.0 | A | 77 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 6d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |