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 smk-labs/claude-plugins --skill publishgit clone --depth 1 https://github.com/smk-labs/claude-pluginsWrote 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/publish)<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/publish"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/publish/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/publish"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/publish.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 | $0.00096 | $0.00723 |
| Opus 5 | $0.00048 | $0.00362 |
| Sonnet 5 | $0.00019 | $0.00145 |
| Haiku 4.5 | $0.00010 | $0.00072 |
Grade C, and why
publish 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.
گزارش را با readable بساز، بعد از تأیید روی پورتال صفحهاش کن، و آخرش یک ایمیل کوتاه به لحن خودم با لینک همان صفحه بده. Use when the user says "منتشر کن", "بذار روی پورتال", "صفحهاش کن", "لینکش کن", "publish this", "put What it actually says
publish: گزارش، صفحه، ایمیل
سه تحویل پشت سر هم. هیچکدام بدون تأیید کاربر به بعدی نمیرود.
-
گزارش. با
/readable:reportیک فایل HTML مستقل بساز. اگر کارتی در چت هست، محتوای همان را عیناً بردار. چون خروجی روی وب میزبانی میشود،--inline-figuresبده. -
تأیید. مسیر فایل را بهصورت لینک بده و بپرس منتشر شود یا نه. تا «بله» نگرفتهای هیچ چیزی آپلود نکن.
-
صفحه. یک دستور، از فایل تا لینک:
node "<this skill dir>/publish.js" <path-to-report.html> [--slug my-report] [--viewer [email protected]]خودش زیپ میکند،
nameرا از<title>سند برمیدارد، وaccess_modeپیشفرضallowlistاست. JSON برمیگرداند؛urlرا به کاربر بده. برای جایگزینی یک صفحهٔ موجود با همان لینک:--page-id <id>. -
ایمیل. یک کارت readable کوتاه بساز، به لحن
/me:write-as-me: دو سه جمله که بگوید این چیست و چرا مهم است، بهعلاوهٔ لینک صفحه. محتوای گزارش را تکرار نکن. آخرش به کاربر بگو از منوی همان کارت گزینهٔ Email را بزند تا آمادهٔ کپی شود.
چرا اسکریپت، نه ابزار MCP
ابزار pages_create_from_zip آرشیو را base64 میگیرد. یک گزارش ۷۵۰ کیلوبایتی با فونت جاسازیشده حدود ۶۳۰ کیلوبایت base64 میشود، یعنی صدهزار توکن که باید از کانتکست رد شود و بایتهایش هم سالم درنمیآید. اسکریپت فایل را از دیسک میخواند و خودش POST میکند، پس هیچوقت pages_create_from_zip یا pages_create_from_text را مستقیم صدا نزن و محتوای فایل را هم نخوان.
-
ورودی میتواند یک فایل، یک پوشه (که باید
index.htmlدر ریشه داشته باشد)، یا یک زیپ آماده باشد. -
لاگین از همان توکنی میآید که
mcp-remoteنگه داشته. اگر گفت لاگین نیست، پیام خودش دستور را میدهد. -
--out file.zipفقط زیپ را میسازد و آپلود نمیکند، برای وقتی کاربر خودش میخواهد آپلود کند. -
زبان هر سه خروجی همان زبان مکالمه است.
-
اگر انتشار شکست خورد، همانجا بگو، فایل گزارش را تحویل بده و جلوتر نرو.
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 · 32 lines · 96 tokens per session scan C 4c12d37c877f
publish is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 3d ago), licensed MIT. It adds 96 tokens to every session and 723 once invoked, about $0.0005 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
brainstorm-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.
ab-test-analysis
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
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.
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.
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…
shipping-artifacts
The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…