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 Buckeyes22/subagent-model-routingnpx agentmods add plugins/buckeyes22/subagent-model-routing/subagent-model-routing-claudegit clone --depth 1 https://github.com/Buckeyes22/subagent-model-routingWrote 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/buckeyes22/subagent-model-routing/subagent-model-routing-claude)<a href="https://agentmods.dev/plugins/buckeyes22/subagent-model-routing/subagent-model-routing-claude"><img src="https://agentmods.dev/badge/plugins/buckeyes22/subagent-model-routing/subagent-model-routing-claude.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
subagent-model-routing-claude 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 4d 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": "subagent-model-routing-claude",
"version": "0.7.1",
"author": { "name": "Buckeyes22" },
"description": "Claude Code package for routing work to non-Claude models: flat one-shot dispatch and dependency-ordered Workflow DAGs over repo-installed codex/kimi/opencode/grok/qwen transport shims",
"keywords": ["subagent-model-routing","claude","subagents","workflow","dag","codex","kimi","moonshot","opencode","grok","xai","qwen","shim"]
}
What it installs
The manifest is a name and a version. 1 skill, 2 commands, 5 agents, 1 hook travel with it, and installing the plugin installs all of them — 660 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.
- 4d ago First seen · 8 lines scan A e9938260ce74
subagent-model-routing-claude is a plugin published in the GitHub repository Buckeyes22/subagent-model-routing (5 stars, last pushed 8d ago), 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 2026-08-31.
Other plugins, from other repositories
swarm
Multi-agent task decomposition and coordination for Claude Code.
swarm
Multi-agent task decomposition and coordination for Claude Code.
open-magi
Magi proposal-first multi-agent deliberation loop for Claude Code.
clankerchat
comms for your coding agents.
unknowns
Skills for discovering and closing knowledge gaps across the dev lifecycle, from Thariq's 'Know Your Unknowns'.
relay
Delegate work packets from a lead Claude Code session to executor sessions in their own iTerm tabs, with session reuse instead of always spawning fresh.