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 skills/squadcodercom/squadcoder/hebrew-rtl-best-practicesnpx skills add squadcodercom/squadcoder --skill hebrew-rtl-best-practicesgit clone --depth 1 https://github.com/squadcodercom/squadcoderWhat 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 | $0.00199 | $0.03487 |
| Opus 5 | $0.00100 | $0.01743 |
| Sonnet 5 | $0.00040 | $0.00697 |
| Haiku 4.5 | $0.00020 | $0.00349 |
Grade A, and why
hebrew-rtl-best-practices 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 2d 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hebrew RTL Best Practices
Instructions
Step 1: Set Up Document Direction
Always start with the HTML attribute (not just CSS):
<html lang="he" dir="rtl">
This tells browsers, screen readers, and CSS to use RTL as the base direction.
Step 2: Use CSS Logical Properties
NEVER use physical directional properties for layout:
| Physical (avoid) | Logical (use) |
|---|---|
margin-left |
margin-inline-start |
margin-right |
margin-inline-end |
padding-left |
padding-inline-start |
padding-right |
padding-inline-end |
border-left |
border-inline-start |
text-align: left |
text-align: start |
text-align: right |
text-align: end |
float: left |
float: inline-start |
left: 10px |
inset-inline-start: 10px |
This ensures the layout automatically mirrors in RTL mode.
When you genuinely need a direction-specific rule that logical properties cannot express, prefer the :dir() pseudo-class over [dir="rtl"] attribute selectors:
/* Modern: matches the resolved direction, including dir="auto" and inheritance */
.chevron:dir(rtl) { transform: scaleX(-1); }
/* Older approach: only matches an explicit dir attribute on/above the element */
[dir="rtl"] .chevron { transform: scaleX(-1); }
:dir() is part of Selectors Level 4 and resolves the computed direction, so it also works for elements whose direction comes from dir="auto" or from an ancestor, where an attribute selector would miss them. Browser support: Chrome and Edge shipped it in version 120 (late 2023), Firefox has supported it for years, and Safari added it in 16.4. For older-browser support, keep an [dir="rtl"] fallback rule or use a logical property instead. Check current support at https://caniuse.com/css-dir-pseudo.
Step 3: Handle Bidirectional Text
When mixing Hebrew and English/numbers:
/* Isolate embedded LTR content */
.ltr-content {
unicode-bidi: isolate;
direction: ltr;
}
/* For inline elements with mixed content */
.bidi-override {
unicode-bidi: bidi-override;
}
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 312 lines · 199 tokens per session scan A 556c65ffb42d
hebrew-rtl-best-practices is a skill published in the GitHub repository squadcodercom/squadcoder (11 stars, last pushed 2mo ago), licensed MIT. It adds 199 tokens to every session and 3,487 once invoked, about $0.0010 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 skills, from other repositories
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready.
patina
Detect and rewrite AI writing patterns in Korean, English, Chinese, and Japanese text so it reads as if a human wrote it. Meaning-preservation (MPS) verified.