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 gitguffaw/codex-routernpx agentmods add plugins/gitguffaw/codex-router/marketplacegit clone --depth 1 https://github.com/gitguffaw/codex-routerGrade A, and why
codex-router 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": "codex-router",
"description": "Live model discovery, policy-backed Codex delegation, and review for Claude Code and AGY.",
"version": "2.4.2",
"owner": {
"name": "Compound"
},
"metadata": {
"description": "Codex Router plugin for live model discovery, policy-backed Codex delegation, and review.",
"version": "2.4.2"
},
"plugins": [
{
"name": "codex-router",
"displayName": "Codex Router",
"description": "Route Claude Code work through Codex with live model discovery, reliable jobs, and explicit policy controls.",
"version": "2.4.2",
"author": {
"name": "Compound"
},
"homepage": "https://github.com/gitguffaw/codex-router#readme",
"repository": "https://github.com/gitguffaw/codex-router",
"license": "Apache-2.0",
"keywords": [
"codex",
"claude-code",
"agy",
"models",
"review",
"delegation"
],
"category": "development-tools",
"tags": [
"codex",
"models",
"review",
"automation",
"agy"
],
"source": "./plugins/codex-router"
},
{
"name": "codex-cli",
"displayName": "Codex CLI",
"description": "A single skill that teaches Claude Code to drive the installed Codex CLI directly, with no companion runtime, hooks, broker, or MCP server.",
"version": "0.1.0",
"author": {
"name": "Compound"
},
"homepage": "https://github.com/gitguffaw/codex-router#minimal-codex-cli-skill",
"repository": "https://github.com/gitguffaw/codex-router",
"license": "Apache-2.0",
"keywords": [
"codex",
"claude-code",
"cli",
"review",
"delegation"
],
"category": "development-tools",
"tags": [
"codex",
"cli",
"review"
],
"source": "./plugins/codex-cli"
}
]
}
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 · 70 lines scan A 0f750a5d707f
codex-router is a plugin published in the GitHub repository gitguffaw/codex-router (2 stars, last pushed 4d 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-stylebooks
Plugin marketplace listing 1 plugin: agent-stylebooks.
subagent-model-routing
Claude Code subagent-model-routing plugin for non-Claude models — flat dispatch + DAG orchestration.
senmu-buildos
Senmu BuildOS plugins for AI project lifecycle governance.
senmu-buildos
Engineering coaching and project governance for AI coding agents: align requirements, reuse frameworks and components, improve code quality, and deliver with evidence.
a-share-mainline-os
Plugin marketplace listing 1 plugin: a-share-mainline-os.
think-it-through
A thinking deck built on the Human-Agent Control Protocol, with 16 composable cards.