Borrowing it
Nothing to install: this file belongs to yechielby/claude-code-rtl-extension. 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/yechielby/claude-code-rtl-extension/master/CLAUDE.mdgit clone --depth 1 https://github.com/yechielby/claude-code-rtl-extensionWrote 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/yechielby/claude-code-rtl-extension/claude-md)<a href="https://agentmods.dev/instructions/yechielby/claude-code-rtl-extension/claude-md"><img src="https://agentmods.dev/badge/instructions/yechielby/claude-code-rtl-extension/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 5.1 | $0.00785 | $0.00785 |
| Opus 5 | $0.00392 | $0.00392 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
claude-code-rtl-extension 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 6d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code RTL Extension
Project Overview
VS Code extension that adds RTL (Right-to-Left) text support for Hebrew, Arabic and Persian to Claude Code's chat interface. Works in VS Code, Cursor, and Antigravity IDEs.
The extension works by injecting CSS and JavaScript into Claude Code's webview files (webview/index.css and webview/index.js). It creates backups before modifying files and can restore them.
Tech Stack
- Language: TypeScript (strict mode)
- Build: esbuild (bundled to single
dist/extension.js, CJS format) - Target: ES2022, Node16 modules
- VS Code API: ^1.94.0
- No test framework — no tests exist in this project
Commands
npm run build— production buildnpm run watch— dev build with watch modenpm run package— create VSIX package via@vscode/vsce
Architecture
Six source files in src/:
| File | Purpose |
|---|---|
extension.ts |
Entry point. Registers commands, handles auto-reactivation on startup, manages global state (mode + version) |
types.ts |
Shared types: ClaudeExtensionInfo, RtlMode, RtlStatus |
finder.ts |
Discovers installed Claude Code extensions on disk across platforms (Win/Mac/Linux/WSL) |
injector.ts |
Core logic: injects/removes CSS+JS into Claude Code files, manages backups, reports status |
content.ts |
All injected CSS rules and JavaScript code as string constants/generators |
statusBar.ts |
VS Code status bar item showing current RTL mode |
RTL Modes
- Active (
active) — CSS scoped to.YBYrtlclass + toggle button (JS) - Always (
always) — CSS without class scoping, no JS button - Auto (
auto) — Per-bubble RTL detection via MutationObserver (JS),.YBYrtlapplied per element - Inactive (
inactive) — RTL removed, original files restored from backup
Key Patterns
- Injected content is wrapped in start/end markers (e.g.
RTL_START_MARKER/RTL_END_MARKER) for clean removal - Files are backed up as
.bakbefore injection; restore from backup on deactivation - Auto-reactivation runs silently on every activation to re-inject after Claude Code updates
- Version tracking in
globalStateprevents stale CSS from stacking - The
.YBYrtlclass is the central CSS scoping mechanism — code blocks, tool output, and thinking blocks are forced LTR
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.
- 6d ago First seen · 64 lines · 785 tokens per session scan A f9fbf535e764
claude-code-rtl-extension CLAUDE.md is an instructions file published in the GitHub repository yechielby/claude-code-rtl-extension (43 stars, last pushed 1mo ago), licensed MIT. It adds 785 tokens to every session, about $0.0039 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 2026-08-30.
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.
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.
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).
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).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.