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.
git clone --depth 1 https://github.com/MSApps-Mobile/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/plugins/msapps-mobile/claude-plugins/rtl-chat-fixer)<a href="https://agentmods.dev/plugins/msapps-mobile/claude-plugins/rtl-chat-fixer"><img src="https://agentmods.dev/badge/plugins/msapps-mobile/claude-plugins/rtl-chat-fixer/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/plugins/msapps-mobile/claude-plugins/rtl-chat-fixer"><img src="https://agentmods.dev/badge/plugins/msapps-mobile/claude-plugins/rtl-chat-fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
rtl-chat-fixer 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.
What it actually says
{
"name": "rtl-chat-fixer",
"version": "0.2.1",
"description": "Fixes jumbled RTL text in Cowork/Claude Desktop chat by teaching Claude how to structure mixed-direction responses for Hebrew, Arabic, Persian, Urdu and other RTL languages.",
"author": {
"name": "Michal Shatz"
},
"keywords": [
"rtl",
"hebrew",
"arabic",
"persian",
"urdu",
"bidi",
"bidirectional",
"chat-formatting",
"sosa-agents"
],
"sosa": {
"compliant": true,
"level": 1,
"impact": "low",
"methodology": "https://github.com/MSApps-Mobile/claude-plugins/blob/main/docs/SOSA.md",
"whitepaper": "https://github.com/MSApps-Mobile/claude-plugins/blob/main/docs/sosa-whitepaper.pdf",
"pillars": {
"supervised": "Fully autonomous — text formatting only",
"orchestrated": "Inline text processing, no external calls",
"secured": "No external access, pure text transformation",
"agents": "R=rtl-text-formatting, T=none, M=none, P=detect-and-format"
}
},
"topics": [
"sosa-agents"
],
"privacy_policy": "https://opsagents.agency/privacy",
"terms_of_service": "https://opsagents.agency/terms"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 126 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 38 lines scan A ac234227c46d
rtl-chat-fixer is a plugin published in the GitHub repository MSApps-Mobile/claude-plugins (10 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
arckit
The Enterprise Architecture Governance Harness - 68 commands across strategy, architecture, delivery, and assurance — including UK Government compliance.
backup-pack
Cross-vendor backup and disaster-recovery assurance — job health monitoring, restore-test verification, retention/RPO compliance, and DR readiness across whatever backup and BCDR tools you have connected.
ai-psychiatry
Semantic executive control for loopholes, underthinking, overthinking, evidence, recursion, context, memory, and reliable delivery.
promptspeak
Pre-execution governance for AI agents. Intercepts MCP tool calls with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.
rad-chrome-extension
MV3 Chrome extension development standards (WXT, React, TypeScript) with two pure-stdlib Python validators that catch what LLM eyeballing misses. Skills cover architecture, MV3 security (CSP, remote code ban, content script isolation), permission minimization and CWS compliance, typed messaging, storage selection…
deep-process-skills
Structured workflows that make LLMs think instead of just respond. Skills for verification, exploration, architecture, risk, feasibility, synthesis, and more.