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.
git clone --depth 1 https://github.com/razzant/claudexorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/razzant/claudexor/claude)<a href="https://agentmods.dev/plugins/razzant/claudexor/claude"><img src="https://agentmods.dev/badge/plugins/razzant/claudexor/claude/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/razzant/claudexor/claude"><img src="https://agentmods.dev/badge/plugins/razzant/claudexor/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
claudexor 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 today.
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": "claudexor",
"description": "Use the local Claudexor control plane for multi-harness planning, execution, and review.",
"version": "4.2.0",
"author": { "name": "Anton Razzhigaev", "url": "https://github.com/razzant" },
"homepage": "https://claudexor.ai/",
"repository": "https://github.com/razzant/claudexor",
"license": "MIT",
"keywords": ["claude-code", "codex", "cursor", "multi-agent", "mcp"],
"skills": "./skills/",
"mcpServers": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 73 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- today Changed 54430ffadaa7
- yesterday Changed a47dcd817bc3
- 3d ago Changed 70bbbc56a69f
- 4d ago Changed 173944fe1969
- 6d ago Changed dc5a201617d0
- 7d ago Changed 69d9cbad058a
- 9d ago Changed 8b3350fae7d7
- 10d ago Changed 30411c20ec3a
- 11d ago Changed e43722f8b462
- 12d ago First seen · 13 lines scan A 876f14d8e1de
claudexor is a plugin published in the GitHub repository razzant/claudexor (509 stars, last pushed today), licensed MIT. 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 2026-10-04.
Other plugins, from other repositories
apple-pim
Native macOS integration for Calendar, Reminders, Contacts, and Mail using EventKit, Contacts, and JXA frameworks.
anycap
Create and understand media, research the live web, share files, and publish pages through the AnyCap CLI and MCP server.
anycap
Multimodal capabilities for AI agents through the AnyCap CLI.
my-daily-skills
my-daily-skills. CodeAuto is an intelligent programming assistant developed using Java, drawing inspiration from Claude Code and Minicode.
lm-resizer
Keep noisy command output (tests, builds, package managers, diffs, logs) out of the context window. Ships the lm-resizer skill and the lm-resizer MCP server (compress, tooloutput, retrieve, stats). Requires the lm-resizer binary on PATH.
xcode-cli
Xcode CLI — Build, test, run, and manage Xcode projects from Claude Code.