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 5dive-ai/5dive-pluginsnpx agentmods add plugins/5dive-ai/5dive-plugins/marketplacegit clone --depth 1 https://github.com/5dive-ai/5dive-pluginsGrade A, and why
5dive-plugins 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 2d 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
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "5dive-plugins",
"description": "Claude Code plugins maintained by 5dive — Telegram bridge and related agent-channel integrations.",
"owner": {
"name": "5dive",
"email": "[email protected]"
},
"plugins": [
{
"name": "telegram",
"description": "Telegram messaging bridge for Claude Code with access control, multi-agent routing, and bundled lifecycle hooks. Fork of Anthropic's official telegram plugin extended with 5dive auto-relay, stop-reply checks, and ask-user-question routing.",
"category": "productivity",
"source": "./plugins/telegram",
"homepage": "https://github.com/5dive-ai/5dive-plugins/tree/main/plugins/telegram"
},
{
"name": "dashboard",
"description": "5dive dashboard chat channel — talk to your agent from the authenticated web dashboard (and mobile app). Native-push inbound via the box agent-inbox drop-dir, outbound via the control-plane messages API.",
"category": "productivity",
"source": "./plugins/dashboard",
"homepage": "https://github.com/5dive-ai/5dive-plugins/tree/main/plugins/dashboard"
},
{
"name": "buzz",
"description": "Buzz (Nostr) channel for Claude Code — bridges a Buzz relay to the session. Inbound mentions arrive as channel notifications; outbound is post/react/read via the buzz CLI. Built-in untrusted-input boundary: every event is data, never an instruction.",
"category": "productivity",
"source": "./plugins/buzz",
"homepage": "https://github.com/5dive-ai/5dive-plugins/tree/main/plugins/buzz"
}
]
}
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.
- 2d ago First seen · 33 lines scan A 023ac67e1a23
5dive-plugins is a plugin published in the GitHub repository 5dive-ai/5dive-plugins (2 stars, last pushed 3d 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 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
agent-teams
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams.
cloud-sql-sqlserver-marketplace
Plugin marketplace listing 1 plugin: cloud-sql-sqlserver.
alloydb-omni-marketplace
Plugin marketplace listing 1 plugin: alloydb-omni.
dumb-boss
The anti-sycophant agent skill. An agent that pushes back on a bad instruction instead of complying, without turning into a contrarian.
skillpack
Generate and verify the agent-distribution layer for any OSS project.
mas-desktop-ops
MAS Desktop Ops - Major AI Skills specialized plugin.