KLIDE CLAUDE.md

KLIDE CLAUDE.md is an instructions file for coding agents from pierreprudh/KLIDE. It costs 8,729 tokens per session, scanned A, original, MIT.

Project context for KLIDE, a code editor being built with Rust and Tauri that puts AI agents alongside normal editing tools.

In plain words
What is it for?
Use it when building KLIDE’s editor, agent panel, layout, colors, themes, or desktop application behavior.
Why use it?
It gives the agent the project’s design goals and explains that technical guidance should suit someone learning desktop development and Rust.

Instructions file

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 instructions/pierreprudh/klide/claude-md
Clone the repo
git clone --depth 1 https://github.com/pierreprudh/KLIDE

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 KLIDE CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pierreprudh/klide/claude-md.svg)](https://agentmods.dev/instructions/pierreprudh/klide/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pierreprudh/klide/claude-md"><img src="https://agentmods.dev/badge/instructions/pierreprudh/klide/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,729 This file is loaded in full into every session.
When invoked 8,729 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.08729 $0.08729
Opus 5 $0.04365 $0.04365
Sonnet 5 $0.01746 $0.01746
Haiku 4.5 $0.00873 $0.00873

Measured 4d ago against content hash c4c593c8f4cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

KLIDE CLAUDE.md 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 4d 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.

CLAUDE.md · 495 lines

How it starts

The opening of the file, as written. The whole thing — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Klide project context

This file is loaded automatically when Claude Code works in this directory. Read it first.

What Klide is

Klide is a code editor Pierre is building from scratch. The goal is a small, fast, AI-first IDE that looks like a 2026 design tool, works like a full-featured code editor, and treats agents as a first-class surface — an editor and an agentic control panel in one shell.

Pierre is new to building desktop apps and is learning Rust as he goes. Frame technical explanations for a smart beginner — explain what each piece does, cite docs, and prefer fewer-moving-parts solutions.

Vision in one sentence

A familiar IDE structure, a calm minimal aesthetic, and fluent AI — Tauri-light, local-model-first, agent-native.

Design philosophy

"Minimalist" here is a visual/UX principle, not a feature-pruning principle.

✅ Do ❌ Don't
Keep the familiar IDE structural layout (sidebar rail, tabs, editor, status bar, panel) Strip out structural elements to "simplify"
Quiet light/dark palettes with shared app + terminal tokens Saturated accent colors, gradients, drop shadows
Generous whitespace, thin 1px borders, no heavy dividers Boxes, frames, busy chrome
Restrained type — Atkinson Hyperlegible for UI, Monaspace for code Multiple display fonts, decorative weights
Subtle, considered motion (fades, no bounces) Springy animations
Icons only when they earn their place Icon-for-every-button maximalism

If a UI element doesn't serve clarity, it doesn't ship.

Stack

Layer Tech Notes
Shell Tauri 2 Rust backend, native webview, 27 MB app bundle (measured 2026-08-24; re-measure with du -sh src-tauri/target/release/bundle/macos/Klide.app)
Editor Monaco via @monaco-editor/react The browser editor core (also used by VS Code)
Terminal xterm.js + Rust portable-pty Real shell, not a sandbox
Frontend React 19 + TypeScript + Vite
Local AI Ollama (localhost:11434) + MLX (mlx_lm.server on :8080) Both run the full tool harness; default llama3.1:8b
Online AI Anthropic, OpenAI, Mistral, xAI, DeepSeek, OpenRouter + self-hosted OpenAI-wire endpoints Keys in macOS Keychain; self-hosted tokens via ${VAR} refs
Auto-install npx skills add <owner/repo> Skill install + uninstall via Rust commands

Read the full file on GitHub · 495 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. 4d ago First seen · 495 lines · 8,729 tokens per session scan A c4c593c8f4cf

Subscribe to this mod's changes

KLIDE CLAUDE.md is an instructions file published in the GitHub repository pierreprudh/KLIDE (5 stars, last pushed 4d ago), licensed MIT. It adds 8,729 tokens to every session, about $0.0436 per session on Opus 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 2026-08-31.