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 vsladkov/claudex-stereonpx agentmods add plugins/vsladkov/claudex-stereo/stereogit clone --depth 1 https://github.com/vsladkov/claudex-stereoGrade A, and why
stereo 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
{
"name": "stereo",
"displayName": "Claudex Stereo",
"version": "1.47.0",
"description": "Pair Claude with the Codex CLI: mixed-model planning and implementation, adversarial reviews, delegated tasks, and background jobs.",
"author": {
"name": "Veselin Sladkov"
}
}
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 · 10 lines scan A 844001fb874c
stereo is a plugin published in the GitHub repository vsladkov/claudex-stereo (3 stars, last pushed 23d 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
project-brain
Folder structure + collaboration protocol so AI sessions can resume project context after compaction or window switch. One brain/ folder, 5 core files (PROJECT/MAP/STATUS/DECISIONS/HANDOFF), and a topic taxonomy.
forge
Decide-then-code. Forge Mentor teaches every load-bearing decision, records your choice, and blocks code from moving past a decision you have not made yet.
rubber-duck
Socratic debugging for AI agents. Don't give me the answer. Help me find it.
maude
Claude's partner inside Claude Code. He writes the code; she notices. No baggage.
maude
Claude's partner inside Claude Code. He writes the code; she notices. She holds the mission you set and flags it the moment he drifts off it, gates irreversible actions before they fire, whispers when he's stuck or hasn't verified, and shows up once every session. No daemon, no database, no backend — she's in your…
volley
Two AI coding assistants in one repo, behind a hard lock. Claude and OpenAI Codex plan, implement, and review each other's work without colliding.