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.
/plugin marketplace add Jacksunwei/claude-telegram-buddynpx agentmods add plugins/jacksunwei/claude-telegram-buddy/plugingit clone --depth 1 https://github.com/Jacksunwei/claude-telegram-buddyGrade B, and why
telegram-buddy scanned grade B with 2 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 yesterday.
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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
"command": "curl -fsS -X POST -H 'Content-Type: application/json' --data-binary @- http://127.0.0.1:52891/approve 2>/dev/null || echo '{}'", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"command": "curl -fsS -X POST -H 'Content-Type: application/json' --data-binary @- http://127.0.0.1:52891/approve 2>/dev/null || echo '{}'", How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "telegram-buddy",
"version": "1.0.0",
"description": "Hand off your Claude Code session from terminal to phone (and back) without losing context",
"author": {
"name": "Wei (Jack) Sun"
},
"license": "Apache-2.0",
"homepage": "https://github.com/Jacksunwei/claude-telegram-buddy",
"repository": "https://github.com/Jacksunwei/claude-telegram-buddy",
"keywords": [
"mcp",
"claude-code",
"permissions",
"telegram",
"hooks",
"remote-approval"
],
"userConfig": {
"telegram_bot_token": {
"type": "string",
"title": "Telegram Bot Token",
"description": "From BotFather: open Telegram, message @BotFather, run /newbot, follow the prompts, copy the HTTP API token.",
"sensitive": true,
"required": true
},
"user_id": {
"type": "string",
"title": "Telegram User ID",
"description": "Your numeric Telegram user ID. To get it: message @userinfobot on Telegram and copy the 'Id' value. Used as both the trust anchor (incoming messages from other users are discarded) and the chat target in DM mode. After install, DM your bot once so Telegram allows it to message you back.",
"required": true
}
},
"mcpServers": {
"telegram-buddy": {
"command": "uv",
"args": [
"run",
"--script",
"${CLAUDE_PLUGIN_ROOT}/server/server.py"
],
"env": {
"TELEGRAM_BUDDY_BOT_TOKEN": "${user_config.telegram_bot_token}",
"TELEGRAM_BUDDY_USER_ID": "${user_config.user_id}"
}
}
},
"hooks": {
"PermissionRequest": [
{
"matcher": ".*",
"hooks": [
{
"type": "command",
"command": "curl -fsS -X POST -H 'Content-Type: application/json' --data-binary @- http://127.0.0.1:52891/approve 2>/dev/null || echo '{}'",
"timeout": 28800
}
]
}
],
"PostToolUse": [
{
"matcher": ".*",
"hooks": [
{
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.
- yesterday First seen · 99 lines scan B 6f7a714ca8ee
telegram-buddy is a plugin published in the GitHub repository Jacksunwei/claude-telegram-buddy (3 stars, last pushed 3mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
zAI-Skills
Development marketplace for AI-Toolkit, consulting-toolkit, real-estate-investment, career-coach, and plugin-forge plugins.
rad-a11y
WCAG 2.2 AA accessibility toolkit for Claude Code. Six skills covering semantic HTML, ARIA patterns, keyboard/focus, forms, automated testing setup, and a static-analysis review pass; one autonomous reviewer agent. Four pure-stdlib Python validators (scan-jsx-patterns, check-tailwind-contrast with real WCAG sRGB ma.
cost-guardian-marketplace
Plugin marketplace listing 1 plugin: cost-guardian.
safe-android-reverser
Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.
clipboard-mcp-server
Read, write, and inspect the system clipboard across macOS, Linux (X11/Wayland), and Windows via MCP. STDIO or Streamable HTTP.
unslop
Three anti-slop scanners in one bundle: a-unslop-text catches AI-diction and cadence tells in prose, a-unslop-code catches bugs and tutorial-shaped patterns in source, a-unslop-ui catches stock-default looks in web UI. Each ships a deterministic scanner plus a Build mode that heads off the tell before it ships. The…