wigi-llm: Instructions file for Claude Code

CLAUDE.md

wigi-llm CLAUDE.md is an instructions file for Claude Code from Platano78/wigi-llm. It costs 747 tokens per session, scanned A, original, MIT.

Project instructions for Wigi-LLM, a set of six C# widgets for a G.SKILL WigiDash touchscreen. The widgets control and monitor local large language model infrastructure, such as a model router and GPU memory.

In plain words
What is it for?
Use them when modifying the WigiDash widgets, launcher configuration, router controls, model dashboards, or GPU-memory monitoring tools.
Why use it?
They explain the project structure, important scripts, and rules before changes are made. This reduces the risk of breaking controls for starting, stopping, or monitoring local models.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions AGENTS.md.

This is Platano78/wigi-llm's own configuration. It tells Claude Code how to work on wigi-llm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything wigi-llm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Platano78/wigi-llm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Platano78/wigi-llm/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Platano78/wigi-llm

Made for: Claude Code.

Wrote 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.

agentmods badge for wigi-llm CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/platano78/wigi-llm/claude-md/github.svg)](https://agentmods.dev/instructions/platano78/wigi-llm/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/platano78/wigi-llm/claude-md"><img src="https://agentmods.dev/badge/instructions/platano78/wigi-llm/claude-md/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.

agentmods 80×15 button for wigi-llm CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/platano78/wigi-llm/claude-md"><img src="https://agentmods.dev/badge/instructions/platano78/wigi-llm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 747 This file is loaded in full into every session.
When invoked 747 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00747 $0.00747
Opus 5 $0.00374 $0.00374
Sonnet 5 $0.00149 $0.00149
Haiku 4.5 $0.00075 $0.00075

Measured 9d ago against content hash e39c08ad92ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wigi-llm CLAUDE.md scanned grade A 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- router-control.sh must work standalone without dependencies beyond curl, bash, and jq
CLAUDE.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wigi-LLM

First, read AGENTS.md in this directory and follow its routing. It is the canonical brain (areas, Inputs tables, pickup/handoff). This file is retained as Layer-3 reference detail (key files, architecture, build rules) for the area you route into.

A widget suite for the G.SKILL WigiDash touchscreen panel providing hardware-level control and monitoring for local LLM infrastructure.

What This Is

Six C# WigiDash widgets that turn the panel into a dedicated control surface for local AI. The daily-driver is the LLM Launcher (config-driven via buttons.json); the rest are experimental — model dashboards, brain monitors, router health, clipboard-to-LLM pipeline.

Key Files

  • scripts/router-control.sh — CLI wrapper for llama.cpp router API (sources vram-utils.sh, calls start-router.sh)
  • scripts/start-router.sh — Router server lifecycle (start/stop/status); the "Router ON" button runs this
  • scripts/kill-all-llm.sh — KILL button script: stops router + flushes VRAM
  • scripts/vram-utils.sh — VRAM helper functions sourced by router-control.sh
  • scripts/gpu-vram-server.py — Remote GPU VRAM HTTP server
  • wigidash/examples/ — Example buttons.json configurations
  • wigidash/icons/ — Pixel art icon set for model buttons
  • wigidash/src/LLMLauncherWidget/ — The daily-driver widget (reads buttons.json at runtime)
  • wigidash/src/Shared/GpuInfo.cs — Shared GPU VRAM detection helper used by the experimental widgets
  • wigidash/src/Shared/WslPaths.cs — Shared WSL POSIX → Windows path translation helper
  • wigidash/src/*Widget/ (all except LLMLauncherWidget) — Experimental C# widgets; the complete, current list lives in the AGENTS.md Areas table

Architecture

Panel → Windows → WSL exec → router-control.sh → llama.cpp router API (port 8081) → GPU Widgets → nvidia-smi.exe (local VRAM) or gpu-vram-server.py (remote VRAM)

Rules

  • Keep buttons.json examples valid JSON at all times
  • router-control.sh must work standalone without dependencies beyond curl, bash, and jq
  • Icons are paired: always provide both icon_name_active.png and icon_name_off.png
  • Do not hardcode user-specific paths — use YOUR_USER placeholders in examples
  • Do not hardcode GPU VRAM sizes — use GpuInfo.cs for auto-detection
  • Do not hardcode personal IPs, usernames, or domains in any shared file
  • C# widgets target .NET Framework 4.7.2 and must reference WigiDashWidgetFramework.dll (HintPath = bare filename, drop the DLL next to the .csproj when building)
  • The experimental widgets link to Shared/GpuInfo.cs via <Compile Include="..\Shared\GpuInfo.cs" Link="GpuInfo.cs" /> — LLMLauncherWidget is self-contained and does NOT depend on it
  • LLMLauncherWidget reads buttons.json from its widget directory at runtime; the JSON is per-user config, never bundled into the DLL
  • LLMLauncherWidget has known hardcoded constants for ROUTER_API_HOST/PORT and LLM_SERVER_PORTS at top of WidgetInstance.cs — fine for now, fix if a user reports needing non-default ports

Read the full file on GitHub · 44 lines

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. 9d ago First seen · 44 lines · 747 tokens per session scan A e39c08ad92ba

Subscribe to this mod's changes

wigi-llm CLAUDE.md is an instructions file published in the GitHub repository Platano78/wigi-llm (2 stars, last pushed 2mo ago), licensed MIT. It adds 747 tokens to every session, about $0.0037 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens