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 useconductor/conductornpx agentmods add plugins/useconductor/conductor/marketplacegit clone --depth 1 https://github.com/useconductor/conductorGrade A, and why
conductor 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 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.
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": "conductor",
"owner": {
"name": "Alexander Wondwossen",
"email": "[email protected]",
"url": "https://thealxlabs.ca"
},
"metadata": {
"description": "Conductor — Universal AI integration hub for Claude Code. Connect to GitHub, Google, Slack, Notion, Spotify, Vercel, HomeKit, and 25+ services.",
"version": "0.1.0"
},
"plugins": [
{
"name": "conductor",
"source": ".",
"version": "0.1.0",
"description": "Universal AI integration hub — connect Claude Code to 25+ services including GitHub, Gmail, Google Calendar, Drive, Slack, Notion, Spotify, Vercel, HomeKit, weather, system info, and more.",
"author": {
"name": "Alexander Wondwossen",
"url": "https://thealxlabs.ca"
},
"homepage": "https://github.com/thealxlabs/conductor",
"repository": "https://github.com/thealxlabs/conductor",
"license": "Apache-2.0",
"category": "integrations",
"keywords": [
"mcp", "github", "google", "gmail", "calendar", "drive",
"slack", "notion", "spotify", "vercel", "homekit",
"automation", "integration", "ai-hub", "weather", "n8n"
]
}
]
}
What ships with it
1 file beside marketplace.json 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.
- yesterday First seen · 34 lines scan A 8f596fc89f2c
conductor is a plugin published in the GitHub repository useconductor/conductor (2 stars, last pushed 4mo 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
livekit-skills
LiveKit Agents SDK skills for voice AI agents on Cloud or self-hosted deployments.
pexo
Plugin marketplace listing 1 plugin: pexo.
sonilo-skills
Sonilo — Agent Skills for licensed music, sound-effects, dubbing, and audio-ducking generation, scored to your video's pacing and emotion.
tdmcp
Plugin marketplace listing 1 plugin: tdmcp.
bevy-skills
AI agent skills for Bevy 0.19: ECS, rendering, physics, input, assets, audio, accessibility, persistence, testing, profiling, voxels, and migration.
motion-design-skills
Motion design fundamentals, engines, and brand elements as installable skills for AI coding agents — timing, typography, color, composition, After Effects, Remotion, logos, and backgrounds.