Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add smk-labs/claude-plugins/plugin install cursor-delegateWrote 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/smk-labs/claude-plugins/copy-writing-fa)<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/copy-writing-fa"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/copy-writing-fa/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/smk-labs/claude-plugins/copy-writing-fa"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/copy-writing-fa.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 | $0.00152 | $0.02072 |
| Opus 5 | $0.00076 | $0.01036 |
| Sonnet 5 | $0.00030 | $0.00414 |
| Haiku 4.5 | $0.00015 | $0.00207 |
Grade C, and why
copy-writing-fa scanned grade C with 1 finding 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 9d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
description: Write Persian web copy (blog articles, product descriptions, landing pages, category text, microcopy, meta titles and descriptions) using Cursor workers, so the writing runs on the Cursor subscription's quot How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
کپیرایتینگ فارسی با ناوگان Cursor
Claude مغز کار است: زاویه، بریف، کلمه هدف، ساختار و پذیرش نهایی. کارگرهای Cursor مینویسند و ویرایش میکنند، روی سهمیه Cursor نه Claude.
مسیر مدلها (اندازهگیری شده، نه حدس)
بیست و پنجم تیر ۱۴۰۵ روی هفت مدل Cursor یک آزمون واقعی گرفتیم: یک بار تولید متن (توضیح محصول + مقاله + سئو + میکروکپی) و یک بار ویرایش یک متن عمدا خراب.
| مرحله | مدل | چرا |
|---|---|---|
| نوشتن | claude-opus-5-high |
بهترین نثر: ریتم متنوع، تصویر مشخص، عمق موضوعی درست. تنها مدلی که سقف کلمه و سقف کاراکتر سئو را رعایت کرد. |
| ممیزی | gpt-5.6-sol-high |
دقیقترین غلطگیر: ۵۰ خطا پیدا کرد، بیشتر از همه. ولی نویسنده خوبی نیست. |
| انبوه | auto |
رایگان و بیسهمیه. برای پیشنویس حجمی کافی است. |
نکتهای که خلاف انتظار درآمد: GPT بهترین مصحح است، نه بهترین نویسنده.
gpt-5.6-sol-high در تولید متن یکنواخت و پرتکرار نوشت و سقف کلمه را شکست؛ در
ویرایش بیرقیب بود. Gemini در نگارش تمیز بود ولی قضاوت تحریری نداشت: ادعای
اثباتنشده و پرسش تبلیغاتی را در بازنویسی نگه داشت.
مرحله ۱ — بریف (کار Claude)
قبل از هر تماس با Cursor، اینها را خودت مشخص کن:
- زاویه: این متن چه چیزی میگوید که رقیب نمیگوید.
- کلمه هدف و دو مترادف.
- ساختار: تیترها به ترتیب، با یک جمله توضیح هر بخش.
- منبع واقعیت: مسیر فایلهایی که کارگر باید از آنها فکت بردارد. برای
seyedmohammad.com یعنی
content/treasury/raw/وdocs/seo/KEYWORD-MAP.md. - طول: از جدول بخش ۹ rulebook.md.
- چیزی که نباید دست بخورد: قیمت، ادعای عددی، فایلهای دیگر.
بریف را کامل بنویس. کارگر Cursor با حافظه خالی شروع میکند و این گفتوگو را نمیبیند.
مرحله ۲ — نوشتن
متن کوتاه (زیر ۴ دقیقه کار): ابزار cursor_run از همین افزونه.
مقاله کامل: اجراکننده لِگدار، چون استریم بلند روی VPN میمیرد.
"${CLAUDE_PLUGIN_ROOT}/scripts/legged-run.sh" \
--cwd <repo> --model claude-opus-5-high "<بریف کامل>"
در متن تسک همیشه این دو خط را بگذار:
قواعد نگارش در
<plugin>/skills/copy-writing-fa/rulebook.mdاست. بخوان و رعایت کن. بعد از نوشتن،python3 <plugin>/scripts/fa-lint.py <file>را اجرا کن و تا وقتی PASS نشده تحویل نده.
What ships with it
1 file 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.
- 9d ago First seen · 131 lines · 152 tokens per session scan C a5db79dfcd5b
copy-writing-fa is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 4d ago), licensed MIT. It adds 152 tokens to every session and 2,072 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
transcreation
Transforms marketing content across languages and markets through transcreation — adapting message, tone, and cultural references instead of translating word for word — while honoring per-locale brand rules and a do-not-translate glossary. Use when localizing content or when a locale is set. Trigger with…
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
pre-mortem
Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go…
outcome-roadmap
Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.
extract-source-sample
Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…
i18n-parity
MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, mirrored READMEs, locale-aware formatting, language switchers) in parity across every supported language. Use automatically (without being asked) whenever you add or change…