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 skills add squadcodercom/squadcoder --skill hebrew-content-writergit clone --depth 1 https://github.com/squadcodercom/squadcoderWrote 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/skills/squadcodercom/squadcoder/hebrew-content-writer)<a href="https://agentmods.dev/skills/squadcodercom/squadcoder/hebrew-content-writer"><img src="https://agentmods.dev/badge/skills/squadcodercom/squadcoder/hebrew-content-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/squadcodercom/squadcoder/hebrew-content-writer"><img src="https://agentmods.dev/badge/skills/squadcodercom/squadcoder/hebrew-content-writer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00175 | $0.03321 |
| Opus 5.5 | $0.00070 | $0.01328 |
| Sonnet 5.5 | $0.00035 | $0.00664 |
| Haiku 4.5 | $0.00017 | $0.00332 |
Grade A, and why
hebrew-content-writer 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 1mo 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.
This is a copy
95% identical to hebrew-content-writer — 43 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hebrew Content Writer
Instructions
Step 1: Identify Content Type and Register
| Content Type | Register | Audience | Key Characteristics |
|---|---|---|---|
| Legal / Government | Formal (gvoha) | Officials, lawyers | Passive voice, complex sentences, traditional gendering |
| Business / Corporate | Business | Professionals | Clear, professional, moderate formality |
| Marketing / Ads | Business-Casual | General public | Persuasive, benefit-focused, concise |
| Direct / Dugri | Dugri | Israeli general public | Blunt, no softeners, short imperative sentences |
| UX / Interface | Direct | End users | Imperative mood, ultra-short, action-oriented |
| Social Media | Informal | Young adults | Casual, slang-friendly, emoji-compatible |
| Blog / Article | Business | Readers | Informative, SEO-aware, structured |
Step 2: Apply Hebrew Grammar Rules
Spelling Standard -- Use Ktiv Maleh (Full Spelling): Modern Hebrew content uses ktiv maleh (plene spelling) with vav and yod for vowels:
- Correct: תוכנה (tochnah) not תכנה
- Correct: שירות (sherut) not שרות
- Follow Academy of Hebrew Language guidelines
Smichut (Construct State) Rules:
- First noun loses definite article: "beit ha-sefer" (the school) not "ha-beit ha-sefer"
- First noun may change form: bayit -> beit, yom -> yom (unchanged)
- Adjectives agree with the LAST noun in the chain
Direct Object Marker (et):
- Required before definite direct objects: "ra'iti ET ha-sefer" (I saw the book)
- NOT used with indefinite objects: "ra'iti sefer" (I saw a book)
- Common mistake: omitting "et" or using it with indefinite objects
Subject-Verb Agreement:
- Verbs agree in gender and number with their subject
- Past tense: also agrees in person
- Present tense: only gender and number (no person distinction)
- Future tense: gender, number, and person
Step 3: Handle Gendered Language
Option A -- Traditional (default for formal/legal): Use masculine plural for mixed groups. Standard in government, legal, academic writing.
What ships with it
4 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.
- 1mo ago First seen · 209 lines · 175 tokens per session scan A 224221294a8d
hebrew-content-writer is a skill published in the GitHub repository squadcodercom/squadcoder (12 stars, last pushed 3mo ago), licensed MIT. It adds 175 tokens to every session and 3,321 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to hebrew-content-writer, differing in 43 lines, and is treated as a copy.
Other skills, from other repositories
write-zot-themes
Help the user create, install, or package zot themes, including theme-only extensions.
suiko
A Japanese writing and review workflow for checking whether text sounds uniform, translated, unnatural, or difficult to read. It supports writing and editing documents such as reports, guides, meeting notes, proposals, and emails.
translations
Translate a Mendix app's user-visible strings with MDL — DESCRIBE TRANSLATIONS to export one file per language, CREATE [OR MODIFY|REPLACE] TRANSLATIONS to write them back. Use when localising an app, filling in a language with an LLM, or auditing which strings are still untranslated. Covers why a translation can be…
writing-git-commits
Write clear, focused Git commit messages and keep commits easy to review.
docutranslate
Use when translating documents locally via LLM — PDF, Word, Excel, Markdown, SRT subtitles with format preservation. DocuTranslate: LLM-powered multi-format local file translation tool with MCP server support.
format-time
Convert UTC timestamps to the user's timezone before showing them in chat, charts, Telegram, or any user-facing output. Use this helper whenever you would otherwise write a raw strftime("%H:%M") of a UTC datetime in something the user reads.