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 agentmods add instructions/pierreprudh/klide/claude-mdgit clone --depth 1 https://github.com/pierreprudh/KLIDEWrote 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/instructions/pierreprudh/klide/claude-md)<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>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 | $0.08729 | $0.08729 |
| Opus 5 | $0.04365 | $0.04365 |
| Sonnet 5 | $0.01746 | $0.01746 |
| Haiku 4.5 | $0.00873 | $0.00873 |
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.
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 |
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.
- 4d ago First seen · 495 lines · 8,729 tokens per session scan A c4c593c8f4cf
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.
Other instructions, from other repositories
ontology-atlas AGENTS.md
AGENTS.md instructions for wlsdks/ontology-atlas, covering agents.md — ontology-atlas, product and non-negotiable architecture, start here, structure and routes and operating gates and skills.
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.
matt-skills-with-to-goal CLAUDE.md
Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
pixir CLAUDE.md
Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.