agentrigs
+ submit rig
~ / rigs / 5dive-ai / 5dive-plugins

5dive-ai/5dive-plugins

Multi-harness plugin marketplace maintained by 5dive — Telegram bridge and related agent-channel integrations.

↗ GitHub ★ 2 Apache-2.0 updated today collection Codex Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~16.4k tokens
Context hog · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add telegram -- bun x @5dive/telegram-codex-mcp@0.5.7

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ claude mcp add telegram -- bun x @5dive/telegram-codex-mcp@0.5.7
$ npx degit 5dive-ai/5dive-plugins/plugins/browser/skills/connect-site .claude/skills/connect-site
$ npx degit 5dive-ai/5dive-plugins/plugins/browser/skills/use-browser .claude/skills/use-browser
$ npx degit 5dive-ai/5dive-plugins/plugins/telegram-agy/skills/notify-user .claude/skills/notify-user
$ npx degit 5dive-ai/5dive-plugins/plugins/telegram/skills/access .claude/skills/access
$ npx degit 5dive-ai/5dive-plugins/plugins/telegram/skills/configure .claude/skills/configure

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

MCP servers (3)

serversourceest. tokens
buzz local / custom 2.5k
dashboard local / custom 2.5k
@5dive/telegram-codex-mcp · "telegram" npm 2.5k

Skills (5)

connect-siteuse-browsernotify-useraccessconfigure

Similar rigs

m1heng/claude-plugin-weixin
—
★ 564 project Claude Code 1 mcp 2 skills 7mo ago
Pragmatist 2.6k tok ·
riasistemas/claude-channel-whatsapp
WhatsApp channel plugin for Claude Code — official Cloud API integration with built-in access control. Built by RIA Systems (verified Meta Tech Provider).
★ 2 project Claude Code 1 mcp 2 skills 5mo ago
Pragmatist 2.6k tok ·
riasistemas/claude-channel-instagram
Instagram channel plugin for Claude Code — official Graph API integration with built-in access control. Modular: public core + optional extensions for CRM / automation. Built by RIA Systems (Meta Tech Provider).
★ 0 project Claude Code 1 mcp 3 skills 5mo ago
Pragmatist 2.7k tok ·
Rich627/whatsapp-claude-plugin
Claude Code WhatsApp channel plugin — run AI directly from WhatsApp, voice transcription, remote tool approval, access control. No API keys, no Docker, just a linked device.
★ 100 project Claude CodeCodex 1 mcp 4 skills 4d ago
Pragmatist 4.9k tok ·
copied ✓