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/skills-il/localization/claude-mdgit clone --depth 1 https://github.com/skills-il/localizationWrote 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/skills-il/localization/claude-md)<a href="https://agentmods.dev/instructions/skills-il/localization/claude-md"><img src="https://agentmods.dev/badge/instructions/skills-il/localization/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 | $0.00585 | $0.00585 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
localization 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- security-compliance CLAUDE.md — 97% identical, 37 lines differ
- developer-tools CLAUDE.md — 94% identical, 37 lines differ
- accounting CLAUDE.md — 91% identical, 37 lines differ
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code when working in this repository.
Project Overview
This is a Skills IL category repository containing AI agent skills for Hebrew localization, RTL layout, and cultural adaptation. Each subdirectory is a self-contained skill following the open Agent Skills standard.
Repository Structure
localization/
├── .github/ # CI workflows, issue/PR templates
├── hebrew-rtl-best-practices/ # Skill: Hebrew RTL Best Practices
│ ├── SKILL.md # Required skill definition
│ └── references/ # Optional documentation
├── hebrew-nlp-toolkit/ # Skill: Hebrew NLP Toolkit
│ └── SKILL.md
├── CLAUDE.md # This file
├── LICENSE # MIT
└── README.md # Category overview
Skill Format (CRITICAL)
Every skill is a folder containing a SKILL.md file. The folder name MUST be kebab-case.
SKILL.md Structure
---
name: skill-name-in-kebab-case # Required, must match folder name
description: >- # Required, <1024 chars, no XML tags
[What it does]. [When to use it — include trigger phrases].
[Key capabilities]. [Optional: Do NOT use for X].
license: MIT # Optional
metadata: # Optional
author: github-username
version: 1.0.0
category: localization
tags: [hebrew, rtl, nlp]
---
Validation Rules
These rules are enforced by CI on every PR:
- File must be exactly
SKILL.md(case-sensitive) - YAML frontmatter must have
---delimiters on both sides namefield: kebab-case only, must match folder namedescriptionfield: present, under 1024 chars, no XML angle brackets, must include WHAT + WHEN- SKILL.md body must be under 5,000 words
- No
README.mdinside skill folders - No skill names containing "claude" or "anthropic"
- No hardcoded secrets
See CONTRIBUTING.md for the full guide.
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 · 72 lines · 585 tokens per session scan A 84bd03ff8c83
localization CLAUDE.md is an instructions file published in the GitHub repository skills-il/localization (23 stars, last pushed 10d ago), licensed MIT. It adds 585 tokens to every session, about $0.0029 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
bob-plugin-ollama-translator AGENTS.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering repository guidelines, project overview, architecture & data flow, key directories and development commands.
VI-Translate AGENTS.md
AGENTS.md instructions for breslee1707/VI-Translate, covering repository guidelines, shared knowledge, working contract and task routing.
evolve-loop GEMINI.md
Gemini CLI instructions for mickeyyaya/evolve-loop, covering project instructions (gemini cli), skill discovery, runtime adapter (tier-1-hybrid), tool name translation and invariants (apply to gemini context too).
KKTerm CLAUDE.md
Claude Code instructions for ryantsai/KKTerm: Constitution, Repository workflow, domain language, source-area boundaries, i18n rules, and engineering defaults live in AGENTS.md. Product terminology lives in CONTEXT.md. Read both before changing behavior or terminology.
cc-rpi AGENTS.md
AGENTS.md instructions for juan294/cc-rpi, covering project: cc-rpi, codex compatibility, command dispatch, claude-to-codex translation and rules and skills.
arty AGENTS.md
Instructions for tleyden/arty, a project described as: iOS realtime voice assistant w/ translation + connectors.